site-audit

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to crawl and analyze external websites. This involves ingesting untrusted HTML and content into the agent's context. An attacker controlling a website could embed malicious instructions (e.g., in HTML comments or hidden text) intended to influence the agent's behavior during the audit process.
  • Ingestion points: scripts/crawl_audit.py fetches HTML content from user-provided URLs.
  • Boundary markers: The skill does not implement explicit boundary markers or sanitization for the ingested content before it is processed by the agent.
  • Capability inventory: The agent has capabilities to write findings to the local filesystem and interact with network APIs.
  • Sanitization: No specific content sanitization is performed on the scraped HTML, though the script itself does not execute the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 06:38 PM