awesome-ai-security-overview
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a URL to fetch the latest curated resource list from the author's official GitHub repository (gmh5225/awesome-ai-security). This is consistent with the skill's purpose as a project overview and maintenance guide.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches external content.
- Ingestion points: The README.md file is fetched from a raw GitHub URL.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided for the fetched content.
- Capability inventory: The skill contains no tools, command execution, or file-write capabilities.
- Sanitization: No sanitization is applied to the fetched content.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found. The mentions of 'Prompt Injection' and 'uncensored models' were correctly identified as descriptive labels for security research categories and do not constitute instruction override attempts.
Audit Metadata