normies
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to visit and process content from external websites, which are untrusted data sources.
- Ingestion points: The 'Agent Prompt Template' in
SKILL.mdinstructs subagents to navigate to a user-specified[URL]using browser tools. - Boundary markers: The skill employs a 'no-code guard' ('Do NOT read any source code or project files') to ensure agents act as visitors and to minimize exposure to potentially malicious hidden code.
- Capability inventory: The agents utilize browser MCP tools to navigate sites and capture screenshots.
- Sanitization: There is no evidence of automated content sanitization or filtering of the website content before it is reviewed by the subagents.
Audit Metadata