burp
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to run the 'burp-agent status' command to verify the state of the local bridge.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external HTTP traffic, which constitutes an attack surface for instructions embedded in data. 1. Ingestion points: HTTP request-response pairs from the local proxy and MCP bridge (SKILL.md). 2. Boundary markers: No specific delimiters or safety instructions for traffic processing are provided. 3. Capability inventory: Replaying network traffic and executing the 'burp-agent' CLI tool (SKILL.md). 4. Sanitization: No sanitization or filtering of captured traffic content is mentioned.
Audit Metadata