bb-methodology
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests and processes untrusted data from external sources such as target websites, JavaScript files, and API responses, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: The methodology instructs the agent to perform 'JS file download' (Phases 1 and 2), 'API mapping' (Phase 2), and 'HTTP probing' (Phase 1) against external, untrusted targets.\n
- Boundary markers: No specific delimiters or instructions are provided to the agent to treat content from these external sources as untrusted or to isolate it from its internal reasoning processes.\n
- Capability inventory: The workflow relies on the agent's ability to execute complex shell commands (e.g.,
curl,subfinder,nuclei,ffuf) and perform network operations based on its findings.\n - Sanitization: The skill lacks instructions for sanitizing or validating external content before it is processed by the agent to determine the next phase of the hunting workflow.\n- [COMMAND_EXECUTION]: The methodology provides extensive lists of command-line tools (e.g.,
amass,rustscan,ghauri,s3scanner) and instructs the agent to use them for active reconnaissance and vulnerability discovery. While these are standard tools for the stated purpose, they represent a significant capability for command execution driven by the methodology's logic.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch content from external, untrusted URLs (JavaScript files, cloud metadata endpoints, etc.) as a core part of the reconnaissance and mapping phases.
Audit Metadata