llvm-security
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch supplemental data from an external GitHub URL (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md) to maintain up-to-date resource knowledge.
- Ingestion points: Data is pulled from the README.md file in the specified repository.
- Boundary markers: Absent; the skill lacks instructions to delimit or specifically handle the untrusted external content.
- Capability inventory: The skill context includes the ability to generate and guide the execution of compiler commands and software analysis tools.
- Sanitization: Absent; there is no validation or filtering process for the remote data.
- [EXTERNAL_DOWNLOADS]: Fetches updated security tool information and project references from a GitHub repository.
Audit Metadata