simple-web-design
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to audit external URLs and HTML code, which constitutes an indirect prompt injection surface.\n
- Ingestion points: Untrusted data enters the agent context through analyzed URLs and user-pasted code as described in
SKILL.md.\n - Boundary markers: The skill contains a dedicated 'Security: Prompt Injection Defense' section in
SKILL.mdthat instructs the agent to treat page content as data and never as instructions.\n - Capability inventory: There are no subprocess calls, file-write operations, or network exfiltration patterns in the provided skill files.\n
- Sanitization:
SKILL.mdprovides a Javascript snippet for URL validation to ensure only safe protocols are used during the audit process.
Audit Metadata