reflect
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from project files to generate reflection documents which could be used to influence future agent actions.
- Ingestion points: The skill reads external data from
specs/<feature>/spec.md,specs/<feature>/plan.md, and git commits to gather feature context. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow for handling external content.
- Capability inventory: The skill performs file system read operations across the project and writes to the
.agent/memory/reflections/directory. - Sanitization: Content gathered from external files is interpolated into reflection templates without sanitization, allowing malicious instructions embedded in source data to potentially influence the agent during reflection generation or during later retrieval by other agents.
Audit Metadata