payloads-lfi-rfi
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve file contents from external web applications using inclusion payloads, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context when it captures and documents the responses (HTTP logs, file contents) from target systems being tested (SKILL.md).
- Boundary markers: The instructions lack delimiters or guidance to treat retrieved content as data rather than instructions, which could lead the agent to follow malicious commands embedded in the files it retrieves (e.g., shell scripts or configuration files).
- Capability inventory: The skill is intended to be used with REA MCP tools that can observe native calls and execute procedures, providing a path for injected instructions to trigger tool usage (SKILL.md).
- Sanitization: There are no documented steps for sanitizing or validating the contents of retrieved files before they are processed by the agent.
Audit Metadata