map-out
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions suggest that the agent use the system
datecommand to generate precise UTC timestamps for its session recording feature. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where it ingests and processes untrusted user data (the 'subject') to perform its analytical tasks.
- Ingestion points: The user-supplied subject via the
/map-outcommand described in README.md. - Boundary markers: No explicit delimiters or safety instructions are defined to separate the user subject from the agent's internal logic.
- Capability inventory: The skill utilizes
file-writeandfile-readcapabilities in SKILL.md for session persistence, and executes thedatecommand for timestamping. - Sanitization: There is no evidence of input validation or escaping for the user-provided subject.
Audit Metadata