w00-workflow-checkpoint
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (
gh) to manage issues (gh issue view,gh issue comment,gh issue list). These commands are used as intended to automate the persistence of workflow states. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external GitHub Issues.
- Ingestion points: Data enters the agent's context when reading issue content and comments via
gh issue view <id> --commentsinSKILL.md. - Boundary markers: The skill instructions do not define delimiters or specific "ignore embedded instructions" warnings for the content retrieved from GitHub.
- Capability inventory: The skill possesses the capability to modify remote resources using
gh issue commentandgh issue createas described inSKILL.md. - Sanitization: There is no specified sanitization, validation, or filtering of the content retrieved from GitHub issues before the agent acts upon it.
Audit Metadata