llvm-learning
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch updated educational resources and lists from the author's GitHub repository at
https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md. As this is a vendor-owned resource (matching the author 'gmh5225'), it is documented as a standard functional reference. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an external remote source, which introduces a vulnerability surface where instructions in that data could influence agent behavior.
- Ingestion points: The agent is directed to fetch content from the remote
README.mdfile in thegmh5225/awesome-llvm-securityrepository (SKILL.md). - Boundary markers: None. There are no instructions to the agent to treat the fetched content as data only or to ignore embedded instructions.
- Capability inventory: The skill provides instructions for the agent to execute shell commands, compile C++ source code into shared libraries, and run LLVM tools (
clang++,opt,clang) (SKILL.md). - Sanitization: None. The skill does not define any validation or filtering for the external content before processing it.
Audit Metadata