negative-case-finder
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for the AI to perform qualitative data analysis. It does not include any scripts, binary files, or calls to external tools.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided research materials such as interview transcripts and coding lists. While this constitutes an attack surface for indirect prompt injection, the skill lacks the capabilities (network access, file system writes) to cause significant harm.
- Ingestion points: User-provided research materials (Supporting material/关锨材料) as defined in SKILL.md.
- Boundary markers: None explicitly defined in the instructions to separate data from system prompts.
- Capability inventory: Text analysis and chat-based output. No file system or network capabilities are requested or used.
- Sanitization: No input sanitization or validation mechanisms are specified.
Audit Metadata