bbot-recon

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed API keys and passwords directly (e.g., passing modules.virustotal.api_key=YOUR_KEY on the command line and NEO4J_AUTH in docker-compose), which encourages the LLM/agent to accept and emit secret values verbatim in commands/configs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). BBOT’s runtime workflow includes OSINT/web modules (e.g., wayback, urlscan, github, urlscan, spider, httpx/nuclei) that fetch and parse third-party web content and pages, which can include outsider-authored free text that is ingested into the scan/LLM context.