autism-support
Pass
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious instruction overrides or bypass attempts were found in the skill documentation.
- [Data Exposure & Exfiltration] (SAFE): No network operations, credential usage, or sensitive file access patterns were identified.
- [Obfuscation] (SAFE): The content is clear and readable with no signs of hidden characters, encoding, or homoglyphs.
- [Indirect Prompt Injection] (INFO): While the skill is designed to process user input regarding child development, it lacks any side-effect capabilities such as file system access or network communication, making the surface area for malicious exploitation negligible.
- [No Code] (INFO): The skill consists entirely of metadata and markdown guidance. No executable scripts, binaries, or logic were found in the provided files.
Audit Metadata