linear
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external sources (Linear tickets and documents) and local files, which could potentially contain malicious instructions intended to influence the agent's behavior.\n
- Ingestion points: The
read-ticket.py,read-document.py, andsearch-issues.pyscripts ingest content from the Linear API. Thecreate-document.pyscript can ingest data from local files via the--content-fileparameter.\n - Capability inventory: The skill has network access to the Linear API and read access to the local filesystem.\n
- Boundary markers: No explicit boundary markers or delimiters are used when processing external or file-based content.\n
- Sanitization: Data is sent as raw strings within GraphQL payloads without specific sanitization for prompt injection patterns.\n- [EXTERNAL_DOWNLOADS]: The skill makes network requests to the official Linear GraphQL API (
api.linear.app). Linear is a well-known project management service.
Audit Metadata