retro
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session logs which are external, potentially untrusted data sources.
- Ingestion points: Session logs on the local machine (referenced in SKILL.md).
- Boundary markers: No specific delimiters or warnings are mentioned to separate log content from retrospective instructions.
- Capability inventory: File system read access for logs, configuration files (package.json, build tools), and CI workflows.
- Sanitization: No explicit sanitization or filtering of external content is described.
- [DATA_EXPOSURE]: The skill accesses local session logs to perform its analysis. This is documented as the primary function of the retrospective tool and does not involve network operations or data exfiltration.
Audit Metadata