draft-gt-command-for-issue-create
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands such as 'git remote -v', 'gt auth status', and 'gt issue list' to obtain repository and authentication metadata.
- [INDIRECT_PROMPT_INJECTION]: The agent ingests data from codebase files to draft issue descriptions, which introduces a surface for indirect prompt injection from potentially malicious content in the repository.
- Ingestion points: Local codebase files and user instructions are used for drafting.
- Boundary markers: There are no specific delimiters defined to separate untrusted codebase content from the agent's instructions.
- Capability inventory: The skill enables file writing to the project's 'tmp/' directory and execution of local 'git' and 'gt' commands.
- Sanitization: The user is required to review the draft and manually run the final command, providing a human-validation step.
Audit Metadata