ckvd-research

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill directs the agent to ingest and summarize external codebase content which may contain untrusted instructions.
  • Ingestion points: Files within src/ckvd/ are read using agent tools like Glob, Grep, and file reading.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential instructions embedded in the code or comments.
  • Capability inventory: The agent has the ability to read filesystem data and generate summaries based on that data.
  • Sanitization: Content from the analyzed files is not sanitized or validated before being processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:44 AM