html-to-interaction-prompts

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external HTML files and live websites.
  • Ingestion points: Analyzes HTML, CSS, and scripts from user-supplied files or live URL references (Framer templates, marketplace pages).
  • Boundary markers: The skill lacks explicit instructions for using delimiters or warnings to ignore malicious instructions that might be embedded in the source HTML or metadata.
  • Capability inventory: The skill has the ability to write files to the local system (article folders), execute media verification via ffprobe, perform git operations (staging/committing), and capture screenshots/video via a browser.
  • Sanitization: There are no documented steps for sanitizing, escaping, or filtering content from the external sources before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:29 AM
Security Audit — agent-trust-hub — html-to-interaction-prompts