web-ctf
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data from web applications and CTF artifacts, creating a surface for indirect prompt injection.
- Ingestion points: Web responses (HTML, JSON, JS), tool outputs from scanners like ZAP or sqlmap, and local challenge artifacts.
- Boundary markers: The skill uses markdown methodology sections to guide the agent but lacks explicit delimiters or instructions to ignore embedded prompts in external data.
- Capability inventory: The skill facilitates the use of numerous offensive tools (sqlmap, nuclei, curl, etc.) and supports file system interactions.
- Sanitization: No specific sanitization or validation logic is defined for data retrieved from external targets before it is processed by the agent.
Audit Metadata