create-checklist
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
gh issue view,git log, andgit show. These commands are used to gather context for generating checklists but interact with external and project data. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it retrieves and analyzes untrusted data from GitHub issues.
- Ingestion points: Content retrieved via
gh issue viewin step 2 ofSKILL.md. - Boundary markers: Absent. There are no instructions or delimiters used to prevent the agent from following commands embedded within the GitHub issue content.
- Capability inventory: The skill has access to the
Bashtool for command execution and theWritetool for file modifications. - Sanitization: Absent. The skill does not perform any validation or sanitization of the issue content before processing it.
Audit Metadata