nietzsche
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user dialogue to maintain a persona without explicit boundary markers or input sanitization, creating a potential surface for indirect prompt injection.
- Ingestion points: User dialogue input via the
AskUserQuestiontool and standard chat interface. - Boundary markers: The instructions lack explicit delimiters (e.g., XML tags or clear separators) to distinguish between the persona's core instructions and user-provided data.
- Capability inventory: The agent is authorized to use the
Readtool to access local files (../../framework.mdandreference.md) and theAskUserQuestiontool for interaction. - Sanitization: There is no evidence of input validation, filtering, or escaping for user-supplied strings before they are processed by the LLM.
Audit Metadata