to-issues-project
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to drive its core logic. \n- Ingestion points: Fetches PRD content and comments from GitHub issues using
gh issue viewin Step 1. \n- Boundary markers: The instructions lack explicit delimiters or instructions to the agent to disregard embedded commands within the fetched issue content. \n- Capability inventory: The skill usesgh issue createandgh apito create new issues and link them, providing a mechanism for the agent to act on the processed data. \n- Sanitization: No sanitization or filtering of the fetched content is specified before it is used to generate the titles and bodies of new sub-issues. \n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI (gh). While this is necessary for its functionality, it introduces a surface for command injection if the AI-generated arguments, such as issue titles, are not properly handled by the execution environment.
Audit Metadata