html-prototype

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product briefs and conversation context to generate HTML artifacts, creating a potential surface for indirect prompt injection.
  • Ingestion points: Processes user conversation, references, and project context as described in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present.
  • Capability inventory: The skill is limited to generating a self-contained .html file. It explicitly forbids external services, APIs, or build tooling in SKILL.md. No subprocess calls or network operations are requested.
  • Sanitization: No specific sanitization or filtering of input data is defined.- [EXTERNAL_DOWNLOADS]: The skill includes a reference to https://docs.plannotator.ai/learn/code-context/html-wireframes-and-prototypes-for-coding-agents. This is an informative link to the author's own documentation site and does not involve the execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 11:51 AM
Security Audit — agent-trust-hub — html-prototype