uw-network-setup
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests multiple untrusted documentation and configuration files which could potentially contain malicious instructions intended to manipulate the agent's behavior during code generation.
- Ingestion points:
docs/ProjectConfig.yaml,docs/TDD_Template.md,docs/CODING_STANDARDS.md, anddocs/NAMING_CONVENTIONS.md(identified inSKILL.md). - Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore potentially adversarial instructions within these files.
- Capability inventory: The skill is capable of generating and writing C# script files and executing the
refresh_unitycommand to re-import assets. - Sanitization: Absent. There are no instructions to sanitize or validate the content of the documentation files before using them to generate code.
Audit Metadata