to-tickets

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill creates local markdown files in the .scratch/ directory and uses configured tools to publish tickets to external platforms like GitHub or Linear. These actions are aligned with the skill's stated purpose.
  • [DATA_EXFILTRATION]: The skill reads project documentation and external URLs to gather necessary context. While it involves data movement, it is limited to the user's project scope and intended tracker.
  • [PROMPT_INJECTION]: The skill processes untrusted input from external URLs and user files, which is a potential surface for indirect prompt injection. A malicious document could attempt to influence the generated ticket content.
  • Ingestion points: Conversation context, local file paths, and external URLs (referenced in SKILL.md).
  • Boundary markers: Not specified in the instructions for wrapping external content.
  • Capability inventory: File system writes to the .scratch/ folder and issue creation on remote trackers via tools.
  • Sanitization: The instructions do not define specific sanitization or filtering for ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 12:41 AM
Security Audit — agent-trust-hub — to-tickets