prototype
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions guide the agent to run project-specific tasks using standard dev tools like
pnpm,python, orbun. This behavior is limited to the local project environment and intended for launching prototypes.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads project documentation (e.g., requirements, backlog) to synthesize prototypes. This constitutes a common attack surface for indirect prompt injection if those files contain malicious instructions, though it is standard for development-focused agents.\n - Ingestion points: Files listed in the project's
AGENTS.md, such asrequirements.mdandbacklog.md.\n - Boundary markers: None specified in the instructions.\n
- Capability inventory: Writing files (HTML, TSX) and executing shell commands via local task runners.\n
- Sanitization: The skill does not describe specific sanitization steps for input document content.
Audit Metadata