epic-management
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell-based templates incorporating the GitHub CLI (
gh) andjqto perform repository management tasks such as creating labels, managing issues, and updating project board fields. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its handling of untrusted data from GitHub issues.
- Ingestion points: The skill reads issue and project data using
gh issue viewandgh project item-list(SKILL.md). - Boundary markers: There are no explicit markers or instructions to treat ingested issue data as untrusted content.
- Capability inventory: The skill has the capability to create, edit, and close issues, as well as modify project board items across the repository (SKILL.md).
- Sanitization: Content retrieved from GitHub is interpolated into shell commands; the skill lacks specific sanitization logic to prevent malicious data in issues from overriding agent instructions or causing command injection.
Audit Metadata