skills/chrisgliddon/bevy-skills/bevy/Gen Agent Trust Hub

bevy

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were identified in this skill.
  • [PROMPT_INJECTION]: The skill contains purely instructional content related to the Bevy game engine. There are no attempts to override agent behavior, bypass safety guidelines, or extract system prompts.
  • [DATA_EXFILTRATION]: There is no access to sensitive file paths (e.g., .ssh, .aws) and no network operations are present. No credentials or secrets are hardcoded.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It references standard Rust crates and tools (e.g., bevy, similarity-rs) which is expected for a developer-oriented skill.
  • [COMMAND_EXECUTION]: The skill does not use shell execution features or privilege escalation techniques like sudo. It mentions a CLI command ('similarity-rs --cross-file') as a suggested developer workflow but does not execute it directly.
  • [OBFUSCATION]: No obfuscated content, such as Base64, zero-width characters, or hidden URLs, was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 01:54 AM
Security Audit — agent-trust-hub — bevy