linear
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from untrusted sources, including repository instructions, a root
LINEAR.mdfile, and active Linear issue content. This data provides project context and configuration that could be manipulated to influence agent behavior.\n - Ingestion points: The
SKILL.mdfile directs the agent to read repository instructions,LINEAR.md, and active issues from the Linear service.\n - Boundary markers: While the skill defines rigorous workflow verification steps, it lacks technical delimiters to isolate untrusted data during processing.\n
- Capability inventory: The agent possesses capabilities to write to the Linear API (creating issues, documents, and comments) and perform git operations, including merging branches.\n
- Sanitization: The instructions do not specify validation or sanitization routines for the data ingested from these external sources.
Audit Metadata