issue-lifecycle
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) alongside system utilities likejqandsedto interact with GitHub projects and issues. These operations (listing items, editing statuses, and posting comments) are legitimate and align with the skill's stated purpose for issue lifecycle management. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading GitHub issue bodies and comments (
gh issue view). This creates an attack surface where instructions embedded within an issue could potentially influence agent behavior. - Ingestion points:
gh issue view [ISSUE_NUMBER] --json bodyinSKILL.md. - Boundary markers: None present in the provided templates; the agent interpolates retrieved issue content directly into shell variables for processing.
- Capability inventory: The skill possesses file-write capabilities (indirectly through issue updates) and command execution via
gh. - Sanitization: No explicit sanitization or filtering of the retrieved issue content is performed before the agent processes it to find and update checkboxes.
Audit Metadata