Initial import of NousResearch/hermes-agent

.github/workflows/supply-chain-audit.yml

@@ -0,0 +1,270 @@
+name: Supply Chain Audit
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+  # No paths filter — the jobs must always run so required checks
+  # report a status (path-gated workflows leave checks "pending" forever
+  # when no matching files change, which blocks merge).
+
+permissions:
+  pull-requests: write
+  contents: read
+
+# Narrow, high-signal scanner. Only fires on critical indicators of supply
+# chain attacks (e.g. the litellm-style payloads). Low-signal heuristics
+# (plain base64, plain exec/eval, dependency/Dockerfile/workflow edits,
+# Actions version unpinning, outbound POST/PUT) were intentionally
+# removed — they fired on nearly every PR and trained reviewers to ignore
+# the scanner. Keep this file's checks ruthlessly narrow: if you find
+# yourself adding WARNING-tier patterns here again, make a separate
+# advisory-only workflow instead.
+
+jobs:
+  # ── Path filter (shared by both scan and dep-bounds) ───────────────
+  changes:
+    runs-on: ubuntu-latest
+    outputs:
+      # True when any file the scanner cares about changed in this PR
+      scan: ${{ steps.filter.outputs.scan }}
+      # True when pyproject.toml changed in this PR
+      deps: ${{ steps.filter.outputs.deps }}
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          fetch-depth: 0
+      - name: Check for relevant file changes
+        id: filter
+        run: |
+          BASE="${{ github.event.pull_request.base.sha }}"
+          HEAD="${{ github.event.pull_request.head.sha }}"
+          SCAN_FILES=$(git diff --name-only "$BASE"..."$HEAD" -- \
+            '*.py' '**/*.py' '*.pth' '**/*.pth' \
+            'setup.py' 'setup.cfg' \
+            'sitecustomize.py' 'usercustomize.py' '__init__.pth' \
+            'pyproject.toml' || true)
+          if [ -n "$SCAN_FILES" ]; then
+            echo "scan=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "scan=false" >> "$GITHUB_OUTPUT"
+          fi
+          DEPS_FILES=$(git diff --name-only "$BASE"..."$HEAD" -- 'pyproject.toml' || true)
+          if [ -n "$DEPS_FILES" ]; then
+            echo "deps=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "deps=false" >> "$GITHUB_OUTPUT"
+          fi
+
+  scan:
+    name: Scan PR for critical supply chain risks
+    needs: changes
+    if: needs.changes.outputs.scan == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Scan diff for critical patterns
+        id: scan
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+
+          BASE="${{ github.event.pull_request.base.sha }}"
+          HEAD="${{ github.event.pull_request.head.sha }}"
+
+          # Added lines only, excluding lockfiles.
+          # Three-dot diff (base...head) diffs from the merge base to HEAD,
+          # so only changes introduced by this PR are included — not changes
+          # that landed on main after the PR branched off.
+          DIFF=$(git diff "$BASE"..."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
+
+          FINDINGS=""
+
+          # --- .pth files (auto-execute on Python startup) ---
+          # The exact mechanism used in the litellm supply chain attack:
+          # https://github.com/BerriAI/litellm/issues/24512
+          PTH_FILES=$(git diff --name-only "$BASE"..."$HEAD" | grep '\.pth$' || true)
+          if [ -n "$PTH_FILES" ]; then
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: .pth file added or modified
+          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required.
+
+          **Files:**
+          \`\`\`
+          ${PTH_FILES}
+          \`\`\`
+          "
+          fi
+
+          # --- base64 decode + exec/eval on the same line (the litellm attack pattern) ---
+          B64_EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|decodebytes|urlsafe_b64decode)' | grep -iE 'exec\(|eval\(' | head -10 || true)
+          if [ -n "$B64_EXEC_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: base64 decode + exec/eval combo
+          Base64-decoded strings passed directly to exec/eval — the signature of hidden credential-stealing payloads.
+
+          **Matches:**
+          \`\`\`
+          ${B64_EXEC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- subprocess with encoded/obfuscated command argument ---
+          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|\\x[0-9a-f]{2}|chr\(' | head -10 || true)
+          if [ -n "$PROC_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: subprocess with encoded/obfuscated command
+          Subprocess calls whose command strings are base64- or hex-encoded are a strong indicator of payload execution.
+
+          **Matches:**
+          \`\`\`
+          ${PROC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Install-hook files (setup.py/sitecustomize/usercustomize/__init__.pth) ---
+          # These execute during pip install or interpreter startup.
+          # Anchored at repo root: only the top-level setup.py/setup.cfg run during
+          # `pip install`, and only top-level sitecustomize.py/usercustomize.py are
+          # auto-loaded by the interpreter via site.py. Any nested file with the
+          # same name (e.g. hermes_cli/setup.py — the CLI setup wizard) is unrelated
+          # and produced false positives that trained reviewers to ignore the scanner.
+          SETUP_HITS=$(git diff --name-only "$BASE"..."$HEAD" | grep -E '^(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          if [ -n "$SETUP_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### 🚨 CRITICAL: Install-hook file added or modified
+          These files can execute code during package installation or interpreter startup.
+
+          **Files:**
+          \`\`\`
+          ${SETUP_HITS}
+          \`\`\`
+          "
+          fi
+
+          if [ -n "$FINDINGS" ]; then
+            echo "found=true" >> "$GITHUB_OUTPUT"
+            echo "$FINDINGS" > /tmp/findings.md
+          else
+            echo "found=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Post critical finding comment
+        if: steps.scan.outputs.found == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          BODY="## 🚨 CRITICAL Supply Chain Risk Detected
+
+          This PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging.
+
+          $(cat /tmp/findings.md)
+
+          ---
+          *Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting.*"
+
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs — GITHUB_TOKEN is read-only)"
+
+      - name: Fail on critical findings
+        if: steps.scan.outputs.found == 'true'
+        run: |
+          echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
+          exit 1
+
+  # Gate: reports success when scan was skipped (no relevant files changed).
+  # This ensures the required check always gets a status.
+  scan-gate:
+    name: Scan PR for critical supply chain risks
+    needs: changes
+    # always() so the gate still reports SUCCESS even if `changes` fails/is
+    # skipped — without it, a failed dependency would leave the required
+    # check unreported (i.e. "pending"), the exact failure mode this fixes.
+    if: always() && needs.changes.outputs.scan != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "No supply-chain-relevant files changed, skipping scan."
+
+  dep-bounds:
+    name: Check PyPI dependency upper bounds
+    needs: changes
+    if: needs.changes.outputs.deps == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Check for unbounded PyPI deps
+        id: bounds
+        run: |
+          set -euo pipefail
+
+          BASE="${{ github.event.pull_request.base.sha }}"
+          HEAD="${{ github.event.pull_request.head.sha }}"
+
+          # Only check added lines in pyproject.toml
+          ADDED=$(git diff "$BASE"..."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
+
+          if [ -z "$ADDED" ]; then
+            echo "found=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          # Match PyPI dep specs that have >= but no < ceiling.
+          # Pattern: "package>=version" without a following ",<" bound.
+          # Excludes git+ URLs (which use commit SHAs) and comments.
+          UNBOUNDED=$(echo "$ADDED" | grep -oE '"[a-zA-Z0-9_-]+(\[[^\]]*\])?>=[ 0-9.]+"' | grep -v ',<' || true)
+
+          if [ -n "$UNBOUNDED" ]; then
+            echo "found=true" >> "$GITHUB_OUTPUT"
+            echo "$UNBOUNDED" > /tmp/unbounded.txt
+          else
+            echo "found=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Post unbounded dep warning
+        if: steps.bounds.outputs.found == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          BODY="## ⚠️ Unbounded PyPI Dependency Detected
+
+          This PR adds PyPI dependencies without a \`<next_major\` upper bound. Per our [supply chain policy](../blob/main/CONTRIBUTING.md#dependency-pinning-policy-supply-chain-hardening), all PyPI deps must be pinned as \`>=floor,<next_major\`.
+
+          **Unbounded specs found:**
+          \`\`\`
+          $(cat /tmp/unbounded.txt)
+          \`\`\`
+
+          **Fix:** Add an upper bound, e.g. \`\"package>=1.2.0,<2\"\`
+
+          ---
+          *See PR #2810 and CONTRIBUTING.md for the full policy rationale.*"
+
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs)"
+
+      - name: Fail on unbounded deps
+        if: steps.bounds.outputs.found == 'true'
+        run: |
+          echo "::error::PyPI dependencies without upper bounds detected. Add <next_major ceiling per CONTRIBUTING.md policy."
+          exit 1
+
+  # Gate: reports success when dep-bounds was skipped (no pyproject.toml changed).
+  # This ensures the required check always gets a status.
+  dep-bounds-gate:
+    name: Check PyPI dependency upper bounds
+    needs: changes
+    # always() so the gate still reports SUCCESS even if `changes` fails/is
+    # skipped — without it, a failed dependency would leave the required
+    # check unreported (i.e. "pending"), the exact failure mode this fixes.
+    if: always() && needs.changes.outputs.deps != 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "No pyproject.toml changes, skipping dependency bounds check."