issue-creation
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from bug reports and feature requests, which is then interpolated into shell-based GitHub CLI commands.
- Ingestion points: Fields such as
Bug Description,Steps to Reproduce,Expected/Actual Behavior, andRelevant Logsdefined inSKILL.mdare populated by user input. - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' directives to prevent the agent from obeying instructions embedded within user reports or logs.
- Capability inventory: The skill utilizes the
gh(GitHub CLI) tool via subprocess calls (gh issue create,gh issue edit) to modify repository state. - Sanitization: Absent. There are no instructions provided to escape, filter, or validate user-provided strings before they are passed to the command-line interface.
Audit Metadata