to-tickets
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to fetch and read content from external sources such as URLs, spec paths, or issue numbers provided in the conversation context.\n
- Ingestion points: Step 1 in SKILL.md fetches content from user-provided URLs, spec paths, and tracker references (issue numbers/comments).\n
- Boundary markers: The instructions do not specify any delimiters, XML tags, or safety markers to isolate the fetched external content from the agent's core instructions.\n
- Capability inventory: The skill has the capability to write to the local file system (repo root) and perform network operations to publish tickets to external issue trackers like GitHub or Linear.\n
- Sanitization: There is no explicit requirement for sanitization, validation, or filtering of the external data before it is interpreted and processed by the agent.
Audit Metadata