to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could lead to indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: External specifications, issue bodies, and comments fetched via URLs or referenced paths (documented in
SKILL.mdunder Step 1: Gather context). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the ingested external data.
- Capability inventory: The skill performs local file writes to
.scratch/and network operations through integration with issue trackers like GitHub and Linear (documented inSKILL.mdunder Step 5: Publish the tickets). - Sanitization: There is no mention of sanitization, filtering, or validation of the fetched external content before it is processed by the agent.
Audit Metadata