Linear SDK Usage
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to fetch data from the external Linear API, which introduces a potential attack surface for instructions embedded in external content.
- Ingestion points: The documentation in
SKILL.mddescribes fetching issue data usingclient.team().issues(). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat fetched data as untrusted content or to ignore potential commands embedded within it.
- Capability inventory: The skill is scoped with access to the
Bashtool as indicated in the YAML frontmatter. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from Linear before the agent processes it.
Audit Metadata