Skills
skills/soul-brews-studio/oracle-skills-cli/oracle-family-scan/Gen Agent Trust Hub

oracle-family-scan

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the gh (GitHub) command-line interface and bun to interact with remote repositories and execute local TypeScript/JavaScript logic. It performs operations such as listing repositories, viewing issues, and posting comments on GitHub. Examples include gh issue view, gh issue comment, and bun $MOTHER/registry/query.ts
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection in its 'welcome' mode. Ingestion points: Data is pulled from external GitHub issue titles and bodies in the Soul-Brews-Studio/oracle-v2 repository. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when passing issue content to the AI agent for personalization. Capability inventory: The skill can post comments to GitHub issues via gh issue comment and execute local scripts via bun and bash. Sanitization: No evidence of sanitization or filtering of the ingested issue body content before it is used to 'craft personalized welcome' messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:48 AM