gsd-spike
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided input through the
$ARGUMENTSvariable to drive its prototyping workflows. While this creates a potential surface for indirect prompt injection where a malicious input could try to influence the agent's behavior, it is a standard design for development-oriented CLI-like skills. - Ingestion points: User input via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: The skill does not use explicit delimiters or "ignore embedded instructions" warnings when interpolating the user input.
- Capability inventory: The skill has access to powerful tools including
Bash,Write,Edit,WebSearch, andWebFetchto perform its prototyping tasks. - Sanitization: No explicit validation or sanitization of the input string is performed within the instruction file, relying on the agent's inherent guardrails.
Audit Metadata