to-tasks

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior or security vulnerabilities were identified. The skill adheres to the principle of least privilege by requesting user confirmation before any mutation.
  • [PROMPT_INJECTION]: Potential indirect prompt injection surface exists because the skill ingests untrusted data from Jira issues and local files. However, the risk is mitigated by a mandatory human-in-the-loop approval process before tasks are created or files are written.
  • Ingestion points: Reads project context from Jira bodies, comments, and local repository files.
  • Boundary markers: None explicitly defined for the input data.
  • Capability inventory: Uses the jira tool to create issues and writes markdown files to .agents/skills/to-tasks/.
  • Sanitization: None, reliance is placed on the mandatory user approval step in 'Quiz the user'.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:06 PM
Security Audit — agent-trust-hub — to-tasks