knowledge-extractor
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is consistent with its stated purpose of summarizing and extracting knowledge from content. No unauthorized file access, credential usage, or malicious command execution was found.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user-supplied text and content from URLs (SKILL.md, Step 1). It lacks explicit boundary markers to isolate untrusted content or specific sanitization steps. This creates a standard surface for indirect prompt injection, which is a low-severity risk typical for content analysis tools.
Audit Metadata