workflow-review-changes

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute local Node.js utility scripts located within the project's hidden directory to manage workflow contracts and review snapshots.
  • Evidence: node .claude/scripts/lib/workflow-skill-contract.cjs --write in SKILL.md.
  • Evidence: node .claude/hooks/lib/review-receipt.cjs snapshot --target=<worktree|staged|commit-descriptor|branch> in references/fix-loop.md.
  • Evidence: node .claude/hooks/lib/review-receipt.cjs issue --kind=workflow-review-changes --scope=full-changeset --snapshot-json='<exact saved JSON>' in references/fix-loop.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (pull requests and code changes) and possesses significant capabilities, creating a surface for potential injection attacks.
  • Ingestion points: The skill reads pull request changes, local project files, and the workflow registry (.claude/workflows.json) as part of its triage and review process.
  • Boundary markers: The provided instructions do not specify explicit delimiters or "ignore instructions" warnings to wrap the code being reviewed.
  • Capability inventory: The skill utilizes spawn_agent for subagent coordination, executes local node scripts, and has full read/write access to project reports and temporary workflow data.
  • Sanitization: There is no evidence of sanitization or escaping of the code content before it is processed by the agent or passed to subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:16 PM