Linear Agents, Sessions and Coding Sessions
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions state that agents should read and follow "Additional guidance" provided by Linear workspaces and teams, which constitutes an ingestion point for untrusted external data.
- Ingestion points: Markdown content from
Workspace: Settings → Agents → Additional guidanceandTeam: team settings → Agents → Additional guidance. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the guidance data.
- Capability inventory: The skill permits the use of the
Bashtool and describes performing actions such as running tests (pnpm test) or opening PRs. - Sanitization: There is no evidence of sanitization or validation for the ingested guidance content.
Audit Metadata