compiler-development
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill directs the agent to fetch resources from an external URL:
https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md. This repository and user are not on the list of Trusted External Sources. - PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) due to its reliance on untrusted external data.
- Ingestion points: The external README.md file referenced in the 'Getting Detailed Information' section.
- Boundary markers: Absent. The skill does not provide delimiters or warnings to the agent to treat the fetched content as untrusted data.
- Capability inventory: The skill is intended for use in environments with compiler toolchains (LLVM), where the agent generates complex code and handles IR generation, providing a significant attack surface if the agent is influenced by injected instructions.
- Sanitization: Absent. The instructions suggest fetching and using the data directly for 'detailed and up-to-date' references.
Audit Metadata