doc-req-fixer

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from potentially untrusted upstream artifacts (Review Reports and SYS documents) to automate document fixes.
  • Ingestion points: Reads from REQ-NN.R_review_report_vNNN.md and SYS files.
  • Boundary markers: Lacks explicit delimiters or instructions for the agent to ignore embedded commands within ingested data.
  • Capability inventory: Possesses capabilities to move files (shutil.move), modify file content (Path.write_text), and execute local shell commands (sha256sum).
  • Sanitization: No mention of input validation or sanitization for content extracted from reports.
  • [COMMAND_EXECUTION]: The skill utilizes local system utilities for administrative tasks.
  • Evidence: Executes sha256sum via shell to perform file integrity checks during drift detection.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:26 AM
Security Audit — agent-trust-hub — doc-req-fixer