extracting-keywords
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
yake,jellyfish,segtok, andregexpackages from the official Python package registry during setup. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text documents from the local file system for analysis.
- Ingestion points: Reads
.txtfiles from/mnt/user-data/uploads/usingopen()andos.listdir()inSKILL.mdexamples. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are included in the prompt templates.
- Capability inventory: The skill performs statistical keyword extraction using the
yakelibrary; it does not perform network operations or write to sensitive system files based on the ingested data. - Sanitization: No input sanitization is performed on the ingested text before extraction.
Audit Metadata