spike-skeleton
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate ('scaffold') and execute integration code to verify architectural connections. While this is performed in restricted directories like
.agents/scratch/, the generation and execution of scripts based on varying architectural requirements is a dynamic execution pattern. - [INDIRECT_PROMPT_INJECTION]: The skill defines a tracer that traverses from an 'Input Port' to a 'Sink', creating an attack surface for data-driven injections.
- Ingestion points: Data entering via the 'Input Port' pipeline (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for data processed during these traces.
- Capability inventory: The agent is authorized to execute commands ('Verification Command') to verify the trace (SKILL.md).
- Sanitization: No specific sanitization, escaping, or validation logic is defined for the input data in the skeleton protocol.
Audit Metadata