ralph-setup
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill provides a command to download content from an external source (https://fullstackrecipes.com/api/recipes/ralph-setup) that is not on the trusted sources list. While this is presented as a 'recipe', downloading arbitrary content via curl is a common precursor to remote code execution.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process user stories in an automated loop to implement features, which establishes an attack surface for indirect prompt injection. 1. Ingestion points: User stories mentioned in the description. 2. Boundary markers: None specified. 3. Capability inventory: Implementation of features and progress logging via agents. 4. Sanitization: None specified.
Audit Metadata