fuzz
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
ffuftool from its official GitHub repository (github.com/ffuf/ffuf/v2) and theseclistscollection via the Homebrew package manager. These are well-known and reputable resources. - [COMMAND_EXECUTION]: The skill leverages the Bash tool to execute
ffufcommands, enabling the agent to perform network-based discovery and testing. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection because it ingests data from external web servers which are then processed by the agent.
- Ingestion points: HTTP response metadata and content returned by target servers during fuzzing operations (SKILL.md).
- Boundary markers: Absent; no specific instructions or delimiters are provided to the agent to treat external tool output as untrusted.
- Capability inventory: The agent has shell execution capabilities via the Bash tool (SKILL.md).
- Sanitization: Absent; there is no mention of sanitizing or validating the responses from external servers before they are analyzed by the agent.
Audit Metadata