plan-website

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill operates as a structured conversational assistant for project documentation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by fetching and processing content from external URLs.
  • Ingestion points: Content retrieved from existing websites and inspiration URLs via WebFetch (SKILL.md).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore commands found within external content.
  • Capability inventory: The agent can perform file writes and edits to the website/ directory and assets folder (SKILL.md).
  • Sanitization: No specific content sanitization or validation logic is defined for the fetched data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:53 AM
Security Audit — agent-trust-hub — plan-website