The Agent Skills Directory

[SAFE]: The skill's primary function is to analyze development sessions and propose documentation updates. It does not require network access, privileged command execution, or access to sensitive local files beyond standard repository documentation.
[INDIRECT_PROMPT_INJECTION]: The skill processes session evidence, including commands and errors, which represents an ingestion point for potentially untrusted data. However, it explicitly instructs the agent to redact credentials, private service details, and user content from the evidence, which serves as a safety control.

retro