cc-yolo-mode

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or metadata.
  • [DATA_EXFILTRATION]: The skill includes explicit safety guardrails to prevent data exposure, specifically banning the committal of secrets, API keys, or credentials to version control (SKILL.md).
  • [COMMAND_EXECUTION]: While the skill utilizes autonomous bash execution ('YOLO mode'), it implements strict limitations such as forbidding 'rm -rf' without confirmation, restricting file modifications to the project directory, and enforcing budget caps (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it ingests data from WebSearch and user-provided specifications.
  • Ingestion points: User-provided project specifications and WebSearch results (SKILL.md).
  • Boundary markers: None explicitly defined for external content.
  • Capability inventory: Includes Bash, Write, Edit, and Agent (SKILL.md).
  • Sanitization: Not explicitly defined, though guardrails provide a secondary layer of protection against dangerous actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:29 PM
Security Audit — agent-trust-hub — cc-yolo-mode