higgsfield-website

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to install the ffmpeg utility using system-level package managers (winget, brew, or sudo apt) for video processing and frame extraction.
  • [COMMAND_EXECUTION]: Uses the claude mcp add command to register the higgsfield and playwright MCP servers locally to the project scope.
  • [EXTERNAL_DOWNLOADS]: Fetches and registers the Higgsfield MCP server from https://mcp.higgsfield.ai/mcp and the Playwright MCP server via npx.
  • [DATA_EXFILTRATION]: Includes a referral link (https://higgsfield.ai/s/mcp-arnold-oberleiter-tNjMkM) that directs users to sign up for the service via the skill author's account.
  • [PROMPT_INJECTION]: The skill manages a surface for indirect prompt injection by ingesting untrusted user descriptions and images to generate code and media prompts.
  • Ingestion points: User interview responses and input images (Phase 1).
  • Boundary markers: Absent; the instructions do not specify delimiters for user-provided data.
  • Capability inventory: Includes shell execution (ffmpeg, npx), external tool calls via MCP, and local file system writes for website assets.
  • Sanitization: No explicit sanitization or validation of user-supplied text is mentioned before it is interpolated into the index.html file.
  • [PROMPT_INJECTION]: Instructs the agent to access and read reference files from another skill's local directory (~/.claude/skills/higgsfield-generate/) to assist with prompt engineering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 12:31 AM
Security Audit — agent-trust-hub — higgsfield-website