add-linear
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches source code from a remote git branch ('origin/channels') and installs the '@chat-adapter/linear' package from the npm registry to enable the Linear integration.- [COMMAND_EXECUTION]: The installation process involves executing shell commands such as 'git fetch', 'git show' for file extraction, and 'pnpm install' for dependency management.- [PROMPT_INJECTION]: An indirect prompt injection surface is created by the catch-all message forwarding logic in 'src/channels/chat-sdk-bridge.ts'.
- Ingestion points: Untrusted comments from Linear issues are ingested via 'chat.onNewMessage(/.*/, ...)'.
- Boundary markers: The skill does not implement delimiters or 'ignore' instructions to distinguish user comments from agent instructions.
- Capability inventory: The agent processes these comments and may use any available tools within its assigned group to respond.
- Sanitization: There is no explicit validation or sanitization performed on the comment content before it is processed by the agent.
Audit Metadata