skyrim-racemenu-followers
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing external data files (presets, sculpt data, and mod archives). This establishes a potential attack surface where untrusted data enters the agent context. Ingestion points: Skyrim mod assets, presets, and sculpt data files. Boundary markers: No explicit instructions are provided to the agent to treat external content as data only or to ignore embedded instructions. Capability inventory: The workflow describes using
skyrim-plugin-authoringand PowerShell/Python scripts for plugin creation and file management. Sanitization: No validation or sanitization of external asset content is mentioned. - [SAFE]: The skill provides legitimate instructions for mod development and does not exhibit patterns of data exfiltration, privilege escalation, or persistence.
Audit Metadata