to-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external sources, which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill reads conversation history, issue tracker bodies/comments, and local specification files as described in the context gathering and codebase exploration steps.
- Boundary markers: Absent; there are no instructions to use specific delimiters or to disregard instructions found within the ingested data.
- Capability inventory: The skill is capable of creating and linking work items (tickets) in an external issue tracking system.
- Sanitization: Absent; the instructions do not specify any validation or sanitization of the content read from external trackers or local files before it is used to generate new tickets.
Audit Metadata