black-tortoise-agent-architecture-quality
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it analyzes external, potentially untrusted project files. \n
- Ingestion points: The skill reads local files including
docs/INDEX.md,AGENTS.md, and project source code. \n - Boundary markers: No explicit delimiters or boundary markers are defined to help the agent distinguish between architectural data and embedded instructions. \n
- Capability inventory: The skill uses Model Context Protocol (MCP) tools for planning and software analysis but lacks instructions for direct network access or sensitive data exfiltration. \n
- Sanitization: No sanitization or filtering logic is specified for the code or documentation being reviewed.
Audit Metadata