burp-extension-development
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface where the agent processes untrusted HTTP traffic as part of its extension development tasks.
- Ingestion points: Burp Suite HTTP requests and responses (referenced in
SKILL.mdandreferences/ui-and-export.md). - Boundary markers: The instructions recommend separating connection metadata (scheme/host/port) from HTTP headers and making conversion limitations explicit.
- Capability inventory: Shell command generation, filesystem indexing, and network communication via the Burp API.
- Sanitization: The skill mandates the use of argument vectors and strict POSIX shell quoting for any user-derived or request-derived data.
- [COMMAND_EXECUTION]: The skill describes methods for integrating with command-line tools by generating shell commands. It provides defensive coding guidance, such as building argument vectors and escaping single quotes for POSIX shells, to mitigate the risk of command injection.
- [EXTERNAL_DOWNLOADS]: The skill refers to official documentation, API artifacts, and template projects from PortSwigger's official domains and GitHub repositories.
Audit Metadata