linear-monitor
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes project data from Linear issues, which constitutes a surface for indirect prompt injection attacks where malicious instructions could be embedded in issue titles or descriptions.
- Ingestion points: Data is ingested through Linear MCP read tools such as list_issues and get_issue as described in SKILL.md.
- Boundary markers: The instructions do not implement explicit delimiters or specialized formatting to isolate untrusted issue content from the agent's core logic.
- Capability inventory: The skill allows the agent to modify the user's workspace by posting comments and updating issue statuses via create_comment and save_issue tools as detailed in METHODOLOGY.md.
- Sanitization: There are no defined procedures for sanitizing, validating, or filtering the data retrieved from Linear before it is evaluated by the agent.
Audit Metadata