Burp Suite Web Application Testing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves the ingestion and analysis of untrusted data from external web applications, which could be leveraged by an attacker to influence the agent's behavior via indirect prompt injection.\n- Ingestion points: The agent is instructed to review and analyze HTTP history, intercepted requests, and server responses within various Burp Suite modules (SKILL.md).\n- Boundary markers: The skill does not provide specific delimiters or safety instructions to distinguish between the testing instructions and the arbitrary content received from web servers.\n- Capability inventory: The skill documentation describes the use of tools for modifying traffic, replaying requests (Repeater), and performing automated scans, which are capabilities that could be abused if the agent follows instructions embedded in malicious web responses.\n- Sanitization: No mechanisms for sanitizing or filtering the content of the captured web traffic are mentioned in the skill.
Audit Metadata