recall

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses git log and grep to perform local history searches. These are standard development tools and their use here is confined to information retrieval within the current repository scope.- [SAFE]: The skill integrates with the ccrider MCP to access past session transcripts. It implements a subagent pattern to process this data, which limits the amount of raw historical data entering the primary agent's context and provides a layer of isolation.- [SAFE]: The skill follows a "least privilege" approach by searching local documentation first before attempting more resource-intensive or broader searches like Git history or session transcripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:40 AM
Security Audit — agent-trust-hub — recall