web-security-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to perform security assessments on external web applications, creating a surface for indirect prompt injection through data ingestion.\n
- Ingestion points: The skill processes external web content, routes, and machine-consumed endpoints through tools like Katana, Burp, and Nuclei (SKILL.md).\n
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore or isolate instructions potentially embedded within the data retrieved from the target application.\n
- Capability inventory: The skill utilizes multiple tools for crawling, request comparison, and vulnerability scanning (/katana, /burp, /nuclei, /api-security-assessment), which are used to analyze and report on external data (SKILL.md).\n
- Sanitization: No explicit instructions for sanitizing, escaping, or validating the data retrieved from external targets are provided within the skill instructions.
Audit Metadata