add-provider
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires gathering configuration details from user-supplied documentation and website URLs. This creates a surface where the agent could ingest and potentially follow malicious instructions hidden within those external documents during the code generation phase.
- Ingestion points:
Required Inputssection inSKILL.md(e.g., docs URL, model list URL). - Boundary markers: Absent; there are no instructions to the agent to disregard instructions found within the external content.
- Capability inventory: The skill modifies several core source files, including
src/main/provider/providerRegistry.tsandsrc/main/provider/defaults.ts. - Sanitization: The workflow does not include a step to validate or sanitize the content retrieved from external URLs before using it to generate source code changes.
Audit Metadata