reviewing-ai-sessions
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted session history data. The risk is mitigated by explicit instructions to treat data as evidence only, ignoring embedded commands, and requiring user approval for all proposed changes.
- [DATA_EXPOSURE]: The instructions include clear guidance to redact secrets and personal details from findings to prevent accidental exposure of sensitive information.
Audit Metadata