recall-reasoning

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local utility scripts (artifact_query.py, artifact_index.py, and search-reasoning.sh) via the shell. These invocations include a query string parameter wrapped in double quotes, which is a standard pattern for local tool interaction.
  • [SAFE]: The skill facilitates access to internal project artifacts such as handoffs, plans, ledgers, and the .git/claude/ directory. This access is scoped to the local environment and intended for project-specific reasoning and history recall. No remote network operations, credential exposures, or obfuscation techniques were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:04 AM
Security Audit — agent-trust-hub — recall-reasoning