nltk-linguistics
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches necessary linguistic models and lexicons, such as 'vader_lexicon' and 'wordnet', from official NLTK servers using the library's standard downloader. This is a common and required setup step for NLP tasks.
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: User-provided text variables are analyzed across tokenization, POS tagging, and sentiment analysis functions in SKILL.md. 2. Boundary markers: None explicitly defined. 3. Capability inventory: The skill is restricted to analytical NLP functions and does not include capabilities for file system writing, subprocess execution, or network exfiltration of the analyzed content. 4. Sanitization: None present. The injection risk is minimal as the processing results are for information only and not used in high-privilege operations.
Audit Metadata