spec-to-issues
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh issue create) to automate the creation of issues. This is core to its described purpose. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: Reads data (titles, descriptions, user stories) from Linear issues using the Linear MCP server.
- Boundary markers: Content from the spec is used to draft issues without explicit boundary markers or instructions to ignore potential injections within the spec text.
- Capability inventory: The skill can create GitHub issues and post comments to Linear issues.
- Sanitization: There is no evidence of content sanitization for the data retrieved from Linear before it is used in the issue creation process.
- [EXTERNAL_DOWNLOADS]: Mentions the Linear MCP server at
https://mcp.linear.app/mcp. This is a well-known service, and the skill includes a safety instruction requiring the user to manually perform the setup rather than executing the configuration command itself.
Audit Metadata