birth
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to check repository status and programmatically create issues with project metadata. - [EXTERNAL_DOWNLOADS]: Includes instructions for the agent to use the
/learncommand on specific GitHub repositories from the author's organization (Soul-Brews-Studio) to retrieve project-specific guidelines. - [PROMPT_INJECTION]: Evaluated for indirect prompt injection surfaces where user-supplied strings are interpolated into system commands.
- Ingestion points: User input for Oracle identity fields (Name, Human, Purpose, Theme) in Step 1.
- Boundary markers: Absent; inputs are placed directly into a markdown template for a GitHub issue.
- Capability inventory: GitHub issue creation via
gh issue createand MCP thread creation viaoracle_threadtool. - Sanitization: Absent; the skill does not specify escaping or validation for user-provided strings before they are written to the repository.
Audit Metadata