hunt-html-injection
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by instructing the agent to fetch and process content from potentially untrusted external web applications during the security testing process.
- Ingestion points: Data reflected or stored in target applications, such as search results, comments, profile fields, and error messages (specified in the 'Attack Surface' section of SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent parses response data from target systems.
- Capability inventory: The skill utilizes the agent's ability to perform network requests and process HTML content to identify unescaped tags.
- Sanitization: There are no instructions for the agent to sanitize or escape the data it retrieves from external targets before processing it.
Audit Metadata