skills/dydoc/skills/to-tickets/Gen Agent Trust Hub

to-tickets

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data which could contain malicious instructions designed to influence the ticket drafting process.
  • Ingestion points: The Gather Context step reads full bodies and comments from user-provided URLs, file paths, or issue references.
  • Boundary markers: No explicit instructions are provided to use delimiters or ignore embedded instructions when reading external content.
  • Capability inventory: The skill has the ability to write local files to the .scratch/ directory and perform network operations to publish tickets to external platforms like GitHub or Linear.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content fetched from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:28 AM
Security Audit — agent-trust-hub — to-tickets