idea-darwin
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external project repository at
github.com/warmskull/idea-darwinand provides installation instructions using the commandclawhub install idea-darwin. - [PROMPT_INJECTION]: The skill is designed to process user-provided content in
ideas.mdandstimuli.md, which represents a surface for indirect prompt injection. * Ingestion points: Local filesideas.mdandstimuli.mdmentioned in SKILL.md. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within these files. * Capability inventory: The agent is instructed to read, score, and expand upon the ideas within these files to generate new content. * Sanitization: No sanitization or validation of the input content is described.
Audit Metadata