llvm-security
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch supplemental data from a third-party GitHub repository (gmh5225/awesome-llvm-security).
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from an external source without sanitization.
- Ingestion points: references/resources.md instructs the agent to fetch a README file from a third-party GitHub URL.
- Boundary markers: There are no markers or instructions to treat the fetched content as untrusted data.
- Capability inventory: The skill primarily provides documentation and shell command examples; no dangerous runtime capabilities like arbitrary file writing or command execution were found.
- Sanitization: No sanitization or validation logic is present for the externally fetched content.
Audit Metadata