llvm-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches additional documentation, curated lists of LLVM optimization commits, and project references from the author's official GitHub repository (
https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md). - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by fetching content from an external source to provide up-to-date resource links.
- Ingestion points:
SKILL.md(Resource section fetch command). - Boundary markers: Absent.
- Capability inventory: None (the skill content consists of documentation and static code examples for local development).
- Sanitization: Absent.
Audit Metadata