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

to-tickets

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from user-supplied references such as specification files, issue numbers, or external URLs to generate tickets. This ingestion of untrusted data creates a potential surface where instructions embedded in those sources could influence the agent's behavior during the ticket generation process.
  • Ingestion points: SKILL.md (Gather context section) specifies fetching and reading the full body and comments of external references.
  • Boundary markers: Absent; there are no instructions to the agent to use delimiters or to ignore instructions contained within the ingested data.
  • Capability inventory: The skill can write files to the local file system (within the .scratch/ directory) and interact with external trackers like GitHub or Linear to publish issues.
  • Sanitization: Absent; the skill does not define any validation, filtering, or escaping for the data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:27 PM
Security Audit — agent-trust-hub — to-tickets