skills/ycs77/skills/to-tickets/Gen Agent Trust Hub

to-tickets

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to assist in task decomposition and project management. Its operations—reading project documentation and creating issue tickets—are consistent with its stated purpose.
  • [PROMPT_INJECTION]: The skill includes a data ingestion surface in Step 1, where it may fetch and process external specifications or issue content. While this creates a potential surface for indirect prompt injection (where instructions hidden in a specification could influence the agent), the skill implements disable-model-invocation: true in its frontmatter, which serves as a significant security control by preventing the agent from autonomously executing tools without oversight.
  • Ingestion points: SKILL.md Step 1 (fetching spec paths, issue numbers, or URLs).
  • Boundary markers: Not explicitly defined in the prompt instructions.
  • Capability inventory: File system writes to the .scratch/ directory and network operations via issue tracker integrations (GitHub, Linear).
  • Sanitization: No explicit sanitization or filtering of external content is described in the prompt text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 08:10 AM
Security Audit — agent-trust-hub — to-tickets