file-issue
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and evaluate existing issue content to perform duplicate searches.
- Ingestion points: Content from existing GitHub issues is ingested via
gh issue listandgh issue viewcommands (Step 2 and Step 6). - Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions to separate ingested issue data from the agent's primary task instructions.
- Capability inventory: The agent is granted the capability to write to the repository using the
gh issue createcommand. - Sanitization: No explicit sanitization or filtering of the ingested issue text is performed before processing.
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the GitHub CLI tool.
- Evidence: The instructions direct the agent to execute
gh issue listandgh issue createusing variable interpolation for parameters such as$repository,$title, and$body_path.
Audit Metadata