kb-search

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs search operations on local markdown files within designated directories. No patterns indicating malicious intent, data exfiltration, or unauthorized command execution were observed.
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by processing external content from project documentation. 1. Ingestion points: Markdown files in docs/kb/ and CLAUDE.md. 2. Boundary markers: Search results are formatted with headers and excerpt markers. 3. Capability inventory: Access is limited to reading files and displaying text; no dangerous system or network tools are used. 4. Sanitization: No explicit content sanitization is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 11:39 AM