manage-wiki

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to interact with a local maestro wiki CLI. This activity is restricted to managing local knowledge graph files and monitoring health statistics.
  • [DATA_EXFILTRATION]: There is no evidence of data exfiltration. The skill does not request network access tools, and all file operations are strictly limited to the .workflow/ directory.
  • [PROMPT_INJECTION]: The skill processes wiki data which is an external input surface susceptible to indirect prompt injection. However, the risk is effectively mitigated by mandatory execution gates, specifically 'Phase Gate 3', which requires explicit user confirmation before any modifications are written to the file system.
  • [SAFE]: The skill follows security best practices for AI agents, including 'read-only by default' behavior and path-based sandboxing for file writes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 08:44 AM
Security Audit — agent-trust-hub — manage-wiki