capture
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies extensively on the GitHub CLI (
gh) to manage labels, issues, and authentication status. These commands are necessary for the skill's primary function of integrating with GitHub. - [EXTERNAL_DOWNLOADS]: The instructions direct users to the official GitHub CLI website (
https://cli.github.com) if the tool is not installed, which is a well-known source for the required tool. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads and processes external content from GitHub issues.
- Ingestion points: Existing issue titles and bodies are fetched via
gh issue listin the--backlogand--listmodes. - Boundary markers: No specific instructions or delimiters are used to separate issue content from the agent's internal instructions.
- Capability inventory: The skill can create or edit GitHub issues and pass data to other skills like
new-raworbrainstorm. - Sanitization: User-provided text is captured verbatim and appended to markdown files (via
--body-file) without escaping or sanitizing potential markdown or instructional payloads.
Audit Metadata