bb-methodology

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The document contains explicit offensive exploitation guidance (payloads, OOB callbacks, SSRF to metadata service, credentials extraction and web-shell/RCE paths) that instructs secret exfiltration and other harmful actions.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill directs the agent to extract/verify API keys and secrets from JS and to include "exact HTTP requests" and paste-ready reproduction commands in reports, which can require the LLM to include secret values verbatim in its output.