groove-utilities-memory-log-daily
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to generate summaries, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested from
git diffoutput, completed task descriptions, and a cache file at.groove/.cache/pending-capture.md(via theSKILL.mdfile's instructions). - Boundary markers: The instructions do not specify the use of delimiters or "ignore" instructions for the ingested content during the summarization process.
- Capability inventory: The skill utilizes
Read,Write,Edit,Glob,Grep,AskUserQuestion, andBash(git:*)across its workflow. - Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested content (such as git commit messages or task resolutions) before it is interpolated into the agent's context for logging.
Audit Metadata