bb-analyze

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for static analysis of project artifacts. It reads local files (spec.md, plan.md, tasks.md, constitution.md) and generates a summary report within the chat interface.
  • [PROMPT_INJECTION]: The skill processes external text from project files, which represents a surface for indirect prompt injection. However, the risk is mitigated by the skill's explicit read-only constraints and the absence of any dangerous capabilities such as shell execution or network access.
  • Ingestion points: Reads content from spec.md, plan.md, tasks.md, and constitution.md via the agent's file reading tools.
  • Boundary markers: None explicitly defined in the prompt instructions to isolate external content.
  • Capability inventory: Limited to file read access and generating markdown output. No file write, network exfiltration, or command execution tools are utilized.
  • Sanitization: No specific sanitization or escaping of the ingested file content is mentioned in the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:49 AM
Security Audit — agent-trust-hub — bb-analyze