adversarial-machine-learning
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a curated list of machine learning security tools and papers located on the author's repository on a well-known hosting platform.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an external repository as a source for supplemental machine learning security data. 1. Ingestion points: SKILL.md (Source: https://raw.githubusercontent.com/gmh5225/awesome-ai-security/refs/heads/main/README.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill does not contain any scripts, tools, or instructions for command execution, network communication, or file system modification. 4. Sanitization: Absent.
Audit Metadata