claude-md-architect

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection as it analyzes untrusted codebase files (e.g., source code, READMEs, package.json) to generate project instructions.
  • Ingestion points: The skill systematically explores and reads project directories and files to identify tech stacks and coding patterns.
  • Boundary markers: There are no defined boundary markers or explicit instructions for the agent to ignore potentially malicious commands embedded within the code it analyzes.
  • Capability inventory: The agent has the capability to write and modify files (creating or updating CLAUDE.md) based on the data it processes.
  • Sanitization: No mechanisms for sanitizing or validating codebase content are specified before the data is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:31 PM