website-audit

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection as it is designed to ingest and process arbitrary content from external URLs.
  • Ingestion points: Website content is systematically fetched during Phase 2 as described in SKILL.md.
  • Boundary markers: There are no instructions to use delimiters or ignore embedded instructions when the agent processes the fetched content for the audit report.
  • Capability inventory: The skill possesses the ability to write to the file system at /mnt/user-data/outputs/ and request user input via the ask_user_input_v0 tool.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation of the fetched website content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 09:05 PM
Security Audit — agent-trust-hub — website-audit