zendesk-macro-effectiveness-scorer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion point for external JSON data, which creates a surface for indirect prompt injection. However, the logic is limited to listing dictionary keys and writing a summary file, with no high-risk capabilities like network access or command execution.
- Ingestion points:
run.pyreads data from a file path provided via the--inputargument. - Boundary markers: The input is processed as structured JSON.
- Capability inventory: The skill is restricted to local file system read/write operations. It lacks subprocess, eval/exec, or network capabilities.
- Sanitization: Input values are not sanitized, but the current scaffold does not process or output the content of those values.
Audit Metadata