kimu-concept-clarifier

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: The skill consists of natural language instructions for linguistic and conceptual analysis. It does not perform any operations involving code execution, file system access, or network communication.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to perform its primary function, representing an ingestion point for untrusted data.
  • Ingestion points: The skill ingests user-provided text via the {概念或原句} placeholder in SKILL.md.
  • Boundary markers: The skill relies on Markdown structure but lacks explicit delimiters or instructions to ignore embedded commands within user input.
  • Capability inventory: The skill is strictly limited to generating text responses and lacks the ability to execute code, access the network, or modify files.
  • Sanitization: The instructions do not define any sanitization or validation logic for the input strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:01 AM
Security Audit — agent-trust-hub — kimu-concept-clarifier