discopy-nlp
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, prompt injections, or security vulnerabilities were detected. The skill instructions are purely focused on legitimate library usage for categorical NLP.
- [EXTERNAL_DOWNLOADS]: The skill installs the
discopypackage via pip, which is a standard procedure for using this research library. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined strings to generate diagrams. Ingestion points: User text in
WordandBoxconstructors. Boundary markers: None. Capability inventory: No dangerous system or network calls. Sanitization: None. The impact is negligible due to the absence of exploitable capabilities.
Audit Metadata