tools-burp-suite
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web applications, creating a surface for indirect prompt injection attacks.
- Ingestion points: The agent reads untrusted data from target applications through tools such as proxy_detail, repeater_send, and intruder_attack as described in SKILL.md and cheatsheet.md.
- Boundary markers: There are no explicit instructions for the agent to use boundary markers or to ignore instructions embedded within the processed web responses.
- Capability inventory: The skill provides the agent with the ability to perform network operations, including sending modified HTTP requests (send_request, repeater_send) and launching automated attacks (intruder_attack), as detailed in cheatsheet.md.
- Sanitization: No sanitization or validation mechanisms are described to filter or escape malicious content within the HTTP responses before they are presented to the agent.
Audit Metadata