idea-darwin
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and documentation. No scripts (Python, JavaScript, Shell) or binaries are included in the skill package.
- [PROMPT_INJECTION]: The skill is designed to ingest and iterate on content from external files like
ideas.mdandstimuli.md. This represents an indirect prompt injection surface where malicious instructions could be embedded in the processed ideas. - Ingestion points: The agent is instructed to read content from
ideas.mdandstimuli.mdto feed the 'evolution' process. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential commands embedded within the user-provided ideas.
- Capability inventory: The skill tasks the agent with performing research, filling logical gaps, identifying risks, and cross-pollinating concepts, which requires deep processing of the untrusted input.
- Sanitization: No sanitization or validation logic is specified for the input data.
Audit Metadata