knowledge-searching

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or high-risk security issues were detected.
  • [NO_CODE]: The skill consists of markdown-based documentation and instructions for utilizing tools, without any accompanying executable scripts or binaries.
  • [PROMPT_INJECTION]: The skill presents an inherent surface for indirect prompt injection by retrieving data from external sources.
  • Ingestion points: Search results from rag_search_knowledge_base and rag_search_code_examples are brought into the agent context.
  • Boundary markers: No delimiters or ignore-instructions are specified for the search outputs.
  • Capability inventory: The skill does not define or request high-risk capabilities such as file-system modification or network exfiltration.
  • Sanitization: No filtering or validation of the retrieved knowledge base content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 03:11 PM