extracting-keywords
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for the 'xberg' tool, specifically focusing on data enrichment tasks like keyword extraction (YAKE/RAKE), language detection, and embedding generation.
- [SAFE]: Instructions for using sensitive data, such as API keys, correctly recommend the use of environment variables (e.g., '$OPENAI_API_KEY') rather than hardcoding credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external document data (e.g., PDF files) for extraction and enrichment. While this represents an ingestion surface for untrusted data, the operations (statistical keyword extraction and language detection) are non-executable and do not represent a significant risk of prompt injection within this context.
- [SAFE]: All referenced tools, packages, and commands (xberg, jq, etc.) are consistent with the vendor's own infrastructure and standard developer utilities.
Audit Metadata