tmp-snapshot
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary 'conversation slices' or user-provided text, which could contain instructions aimed at influencing the agent's behavior during the file-writing process. However, because the skill's capability is limited to writing to the
/tmp/directory, the associated risk is low.
Audit Metadata