full-send
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill serves as an orchestrator that passes untrusted user inputs to powerful sub-skills ($full-stop and $babysit-pr). Ingestion points: User-provided tasks, constraints, and criteria processed in SKILL.md. Boundary markers: The skill does not define clear delimiters or markers to separate instructions from data. Capability inventory: The skill delegates high-impact actions like PR creation and maintenance. Sanitization: No explicit validation or sanitization of input data is described.
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration files with no accompanying executable scripts or binary files.
Audit Metadata