doc-tasks-autopilot

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like ls to verify the existence of folders and executes a local Python script ai_dev_flow/scripts/update_traceability_matrix.py to update project metadata.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes content from specification documents (SPEC, TSPEC).
  • Ingestion points: Reads SPEC and TSPEC documents from the filesystem.
  • Boundary markers: No specific delimiters are used to separate document content from agent instructions.
  • Capability inventory: File system writing and local command execution.
  • Sanitization: No sanitization of input document content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:26 AM
Security Audit — agent-trust-hub — doc-tasks-autopilot