api-key-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill creates a surface for indirect instruction injection because it is designed to manage sensitive keys and security patterns while possessing high-privilege capabilities.
  • Ingestion points: Potential untrusted data enters the context via user requests or external configuration files read using the Read tool.
  • Boundary markers: The skill definition lacks explicit delimiters or instructions for the agent to ignore instructions embedded within the processed data.
  • Capability inventory: The skill allows access to Bash(npm:*), Read, Write, and Grep, enabling comprehensive file system manipulation and command execution.
  • Sanitization: There are no defined logic steps to sanitize or validate the content of managed API keys or security configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM