linear
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain malicious instructions.
- Ingestion points: Data is ingested through commands like
linear issue listandlinear issue view, which fetch issue titles, descriptions, and comments from the Linear platform. - Boundary markers: The instructions do not define explicit boundary markers or delimiters to separate fetched issue content from agent instructions.
- Capability inventory: The skill relies on shell command execution for issue management (
linear) and repository history (git). - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from Linear issues before it is processed by the agent.
Audit Metadata