linear-automation
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Linear issues and comments, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Tools such as
LINEAR_GET_LINEAR_ISSUE,LINEAR_LIST_LINEAR_ISSUES, andLINEAR_SEARCH_ISSUES(referenced in SKILL.md) ingest content from external Linear workspaces into the agent's context. - Boundary markers: The instructions do not specify the use of boundary markers or explicit prompts to ignore instructions embedded within the retrieved issue descriptions or comments.
- Capability inventory: The skill includes write-access tools such as
LINEAR_CREATE_LINEAR_ISSUE,LINEAR_UPDATE_ISSUE, and the ability to execute GraphQL mutations viaLINEAR_RUN_QUERY_OR_MUTATION(referenced in SKILL.md). - Sanitization: No explicit sanitization or validation steps are defined for processing external issue content before it is used to inform further agent actions.
Audit Metadata