html

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the ingestion of untrusted repository documentation.
  • Ingestion points: The skill is instructed to inspect files such as AGENTS.md, CLAUDE.md, and design-system documentation within the user's workspace to derive design language and conventions.
  • Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore natural language instructions that might be embedded within these documentation files.
  • Capability inventory: The agent possesses the capability to write .html files (containing potentially malicious JavaScript if influenced) and use browser tooling to open and exercise those files.
  • Sanitization: There is no evidence of content sanitization or validation for the data pulled from the repository environment before it is used to influence the agent's code generation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 11:51 AM
Security Audit — agent-trust-hub — html