linear-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources which creates a potential surface for indirect prompt injection.\n
- Ingestion points: Documentation and metadata are fetched via WebFetch from linear.app. API responses and GraphQL errors are read during authentication verification.\n
- Capability inventory: The skill uses Write and Edit tools to update repository configuration files and code.\n
- Boundary markers: The instructions explicitly forbid writing credentials or unredacted variables and require explicit owner approval for non-read-only actions.\n
- Sanitization: Mandatory redaction of sensitive fields and credential values is required for all output.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and package metadata from the official Linear service domains.\n
- Evidence: References to linear.app domains for documentation index, GraphQL schema, and authentication guidelines.
Audit Metadata