linear-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions emphasize security best practices, including the redaction of sensitive information and the use of secret managers for credential storage.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Linear workspaces, which could contain untrusted instructions.
- Ingestion points: GraphQL API data from Linear (SKILL.md, references/official-docs.md).
- Boundary markers: The skill requires a read-only diff and explicit owner approval before any mutations.
- Capability inventory: File system modification tools (Write, Edit) and network access (WebFetch).
- Sanitization: Instructions explicitly require that sensitive fields and GraphQL variables be redacted.
Audit Metadata