session-to-skill
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill instructions explicitly direct the agent to redact secrets, credentials, and personal data from the captured workflow before formalizing it into a skill.
- [COMMAND_EXECUTION]: The skill performs file system operations (creating directories and writing files) to save the generated skill. These operations are the primary intended function of the skill and are gated by multiple user approval steps.
- [PROMPT_INJECTION]: The skill processes session transcripts, which constitutes ingestion of untrusted data. This surface for indirect prompt injection is mitigated by mandatory user review of both the workflow outline and the final drafted skill before any files are written to disk.
Audit Metadata