linear-release-control
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from GitHub (Issues, Pull Requests, CI logs) to update Linear. This ingestion of potentially untrusted external content creates a surface for indirect prompt injection.
- Ingestion points: External data enters the context from GitHub issue content, PR descriptions, and CI logs (SKILL.md).
- Boundary markers: None explicitly defined to delimit external data from instructions.
- Capability inventory: Uses the Linear MCP to perform write operations (Linear Project Update) based on external data (SKILL.md).
- Sanitization: No specific sanitization or validation of the external content is prescribed before it is used to generate updates.
- [EXTERNAL_DOWNLOADS]: The skill references official external endpoints for interacting with the Linear platform.
- Evidence: Integration is performed via official Linear MCP endpoints at "https://mcp.linear.app/mcp" and "https://mcp.linear.app/mcp/readonly".
Audit Metadata