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
topicfield in thejokeFlowaction withinSKILL.mdallows 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 thetopicvariable. - 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