skyrim-nexus-publishing
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize technical information from external, potentially untrusted sources such as project build files, mod archives, and logs, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill reads from
ENVIRONMENT.md,TASK.md, ESM/ESP/DLL files, and mod archives to derive feature lists and technical architecture. - Boundary markers: There are no specified boundary markers or instructions to treat data from these external files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill interacts with the
nexus-*workflow andvisual-verificationtools to generate public documentation and media plans. - Sanitization: The instructions lack guidance on sanitizing or escaping content derived from these external files before interpolating them into the agent's context.
Audit Metadata