recurse-ml
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempt to override agent behavior or bypass safety constraints. The instructions are purely pedagogical.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network requests are present in the analyzed content.
- [Remote Code Execution] (SAFE): The skill contains no shell commands, remote downloads, or dynamic code execution patterns. All referenced resources appear to be local markdown files.
- [Obfuscation] (SAFE): No encoded strings, homoglyphs, or zero-width characters were found.
- [Indirect Prompt Injection] (SAFE): The skill provides coding standards for the agent to follow and does not define a mechanism for ingesting untrusted external data.
Audit Metadata