ticket-to-spec

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from ticket bodies and comments, creating a vulnerability to indirect prompt injection where malicious instructions could influence agent behavior.
  • Ingestion points: As described in SKILL.md, the agent reads the full ticket body, user comments, and the current conversation history.
  • Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent distinguish between administrative instructions and untrusted data from the tickets.
  • Capability inventory: The skill is granted the capability to append content to tickets and update ticket metadata (removing the 'needs-details' state) based on synthesized information, as noted in SKILL.md.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the ingested external data before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:38 AM
Security Audit — agent-trust-hub — ticket-to-spec