linear-manager
Warn
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill script
linear.mjsis designed to access the.envfile to retrieve theLINEAR_API_KEY. This involves reading a sensitive file path that typically contains private credentials. - [PROMPT_INJECTION]: The skill provides a vector for indirect prompt injection by retrieving and displaying external content from the Linear API.
- Ingestion points: Issue titles, descriptions, and project data are fetched through
linear.mjs. - Boundary markers: No delimiters or protective instructions are utilized to isolate untrusted external content from the agent's instruction stream.
- Capability inventory: The skill performs subprocess execution through the
npm run linearcommands, which can be influenced by instructions embedded in the external data. - Sanitization: Data retrieved from Linear is presented without validation or sanitization.
Audit Metadata