to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources which creates a surface for indirect prompt injection.
- Ingestion points: Step 1 (Collect Context) instructions the agent to read external content from user-provided references, including specification paths, issue numbers, and external URLs, along with all associated comments.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested external content.
- Capability inventory: The skill possesses the capability to write to the local file system (creating Markdown files in the
.scratch/directory) and to perform network operations by publishing issues to external trackers like GitHub and Linear. - Sanitization: The instructions do not include specific sanitization or validation steps for the content retrieved from external specifications or comments before it is used to generate tasks.
Audit Metadata