retro
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session logs which are external, potentially untrusted data sources.
- Ingestion points: The agent reads primary session sources and searches through session logs on the machine as described in SKILL.md Step 2.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the log files.
- Capability inventory: The skill utilizes file system read access, log searching, and the ability to call other skills.
- Sanitization: No specific sanitization, filtering, or escaping of the log content is implemented before processing.
Audit Metadata