doc-intel-llm-tier-pl

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the contextgem Python package (>=0.25.1) for its core functionality. This dependency is explicitly documented and corresponds to the library cited in the attribution metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document content, which represents a potential attack surface for indirect prompt injection. Ingestion points: Files are ingested through the --text and --docx parameters in scripts/ekstrakcja_llm.py. Boundary markers: The wrapper script does not implement custom delimiters, delegating prompt framing to the contextgem library. Capability inventory: The skill possesses capabilities for reading local files and initiating network connections to LLM backends (local or cloud). Sanitization: Standard input handling is used without specific sanitization of the text before it is passed to the extraction model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:31 PM
Security Audit — agent-trust-hub — doc-intel-llm-tier-pl