linear-graphql-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Linear issues, projects, teams) which are potentially attacker-controlled.
- Ingestion points: Operations like
query/issues,query/issue, andquery/projectsfetch text content from the Linear API (SKILL.md). - Boundary markers: The skill does not specify explicit delimiters or "ignore" instructions for the agent when processing fetched data, although it does instruct the agent to confirm user intent before performing write operations (SKILL.md).
- Capability inventory: The skill provides significant write capabilities including
mutation/issueCreate,mutation/issueUpdate, andmutation/commentCreate, allowing the agent to modify the state of the Linear workspace (SKILL.md). - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from Linear before it is processed by the agent.
Audit Metadata