dart-genkit

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions define an orchestration flow (jokeFlow) that interpolates user-controlled data into a prompt string without adequate isolation or boundary markers.
  • Ingestion points: The topic field in the jokeFlow action within SKILL.md allows external input to enter the agent context.
  • Boundary markers: The prompt template ('Tell me a structured joke about $topic.') lacks delimiters or instructions to ignore potential commands embedded in the topic variable.
  • Capability inventory: The skill lacks dangerous capabilities such as filesystem writes, shell command execution, or non-whitelisted network operations; it primarily uses the LLM and a basic math tool.
  • Sanitization: No input validation, filtering, or escaping is performed on the user-supplied string before it is sent to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 07:04 AM
Security Audit — agent-trust-hub — dart-genkit