recipe-build

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands to verify the presence of project documentation and task files.
  • Evidence: Uses ls -la docs/plans/*.md and ls docs/plans/tasks/*.md to check prerequisites.
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection through the ingestion of external task and plan files.
  • Ingestion points: Reads work plans and atomic tasks from docs/plans/ and docs/plans/tasks/ (SKILL.md).
  • Boundary markers: Absent. The skill does not use delimiters or instructions to prevent the agent from obeying commands embedded within the processed files.
  • Capability inventory: The skill can invoke sub-agents for code execution (task-executor), perform quality checks, and execute git commits.
  • Sanitization: Absent. There is no evidence of validation or filtering of the content read from the task files before they are passed to sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:02 AM