bb-methodology
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external targets, such as HTTP response bodies, JavaScript files, and API metadata, which creates a surface for indirect prompt injection where an attacker could influence the agent's behavior.
- Ingestion points: Target web responses, subdomains, and API outputs analyzed during the Mapping and Discovery phases.
- Boundary markers: The skill mentions specific rules for identifying findings but lacks explicit instruction-data delimiters for all ingested content in this file.
- Capability inventory: The skill utilizes network tools for reconnaissance and vulnerability verification, and file system access for logging and reporting.
- Sanitization: Refers to the use of a separate 'evidence-hygiene' skill for redacting sensitive information like PII before reporting.
- [COMMAND_EXECUTION]: The methodology orchestrates the use of numerous external security tools (e.g., subfinder, nuclei, ffuf, ghauri, aws CLI) for automated scanning and manual validation. These tools are executed using parameters derived from external target reconnaissance.
Audit Metadata