connector-certification-program
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a workflow for reading and writing to a local context file (developer-platform-context.md) to maintain persistent memory. 1. Ingestion points: developer-platform-context.md is read at the start of the project. 2. Boundary markers: Absent. 3. Capability inventory: The skill is limited to generating text charters and recording configuration values in the context file; it lacks capabilities for arbitrary command execution, network access, or dynamic code loading. 4. Sanitization: No sanitization or validation of the ingested context data is specified.
- [SAFE]: No other security concerns were identified. The skill consists of best-practice guidance, evaluation test cases, and benchmarks from well-known technology companies.
Audit Metadata