prototype
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest the user's prompt and the surrounding project code to decide which prototyping logic to apply. This creates an attack surface where malicious instructions hidden in the codebase could influence the agent's behavior. * Ingestion points: User prompts and surrounding project code are evaluated to determine the prototype branch (SKILL.md). * Boundary markers: The skill does not define delimiters or explicit instructions to treat the ingested project code as untrustworthy. * Capability inventory: The agent is authorized to generate new files (HTML, TSX) and suggest task-runner commands (SKILL.md, LOGIC.md, UI.md). * Sanitization: There is no requirement for the agent to validate or sanitize inputs from the environment before they are used to generate prototype code.
- [NO_CODE]: The skill consists entirely of markdown documentation and YAML metadata. No executable scripts, binaries, or active code files are included in the skill distribution.
Audit Metadata