search-corpus
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a search workflow across a local directory (
corpus/). It provides specific ranking and filtering logic (e.g., excluding 'dead' files by default) and limits output to first-sentence excerpts to maintain privacy. There are no indications of prompt injection, data exfiltration, or unauthorized command execution. The logic is entirely confined to the agent's internal processing of its own data corpus.
Audit Metadata