simready-foundation-add-feature-adapter
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to perform its primary function.
- Ingestion points: Reads and processes source/target feature manifests, profile paths, and
test_assets(USD files) as inputs inSKILL.md. - Boundary markers: No explicit instructions are provided to the agent to ignore or delimit embedded instructions within the processed USD data or manifests.
- Capability inventory: The skill instructs the agent to create and save new Python adapter files and update repository indexes, involving file system write operations.
- Sanitization: The instructions do not specify sanitization or validation steps for input data before it is interpolated into the code generation process.
- [SAFE]: The skill's behavior is consistent with its stated purpose and the author's organization (NVIDIA). No instances of command execution, exfiltration, or persistence were found.
Audit Metadata