linear-review
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes external command-line utilities to perform static analysis and security auditing on the target repository.
- Evidence: In
agents/reviewer.md, the skill specifies the execution of tools likeknip,ts-prune,npm audit,osv-scanner, anddepcheckas part of its automated review pipeline. - [PROMPT_INJECTION]: The skill processes untrusted content from external repositories and pull requests, which creates a surface for indirect prompt injection.
- Ingestion points: The agent reads code snippets and diffs directly from the repository under review (
SKILL.md). - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to separate the code being analyzed from the reviewer agent's instructions.
- Capability inventory: The agent has the ability to create and update issues in Linear via the Linear MCP and execute local commands for analysis (
agents/reviewer.md). - Sanitization: The instructions do not describe any sanitization or validation of the ingested code content before it is processed by the AI subagents.
Audit Metadata