bevy

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGH
Full Analysis
  • SAFE (SAFE): No malicious patterns or security vulnerabilities were detected in the four reference markdown files provided.
  • PROMPT_INJECTION (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found in the documentation or code comments.
  • DATA_EXFILTRATION (SAFE): No hardcoded credentials, sensitive file paths, or external network operations were identified within the code snippets.
  • REMOTE_CODE_EXECUTION (SAFE): No use of external package managers, runtime compilation of untrusted data, or remote script downloads was detected.
  • INDIRECT_PROMPT_INJECTION (SAFE): The skill serves as reasoning context for the agent and does not ingest untrusted external data or possess capabilities (such as file-write or network access) that would create an exploitable attack surface.
  • INFO (LOW): Automated scan alerts included in the prompt metadata mentioned malicious URLs in main.rs and combat.rs; however, these files were not part of the provided skill content and no corresponding malicious patterns were found in the documentation files themselves.
Recommendations
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 07:08 AM