retro
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely on local files within the project environment (e.g.,
knowledge/learnings.md,output/retro/) for recording and retrieving retrospective data. - [SAFE]: Explicit instructions are provided to prevent data hallucination, requiring the agent to tag data as
[DATA],[STATED], or[HYPOTHESIS]and prohibiting the use of unverified hypotheses in shared knowledge files. - [SAFE]: The skill mandates a human-in-the-loop confirmation step before writing any updates to the primary learning file, ensuring the user reviews the exact content to be persisted.
- [SAFE]: No obfuscation, external network requests, or dangerous command execution patterns were detected in the instructions or metadata.
Audit Metadata