copilot-usage-metrics
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill invokes the
ghCLI via shell scripts using arguments (org name, enterprise slug, and date) provided by the user. While the variables are double-quoted to prevent shell injection, the lack of validation on these inputs allows for potential path manipulation within the GitHub API request. - [PROMPT_INJECTION] (LOW): The skill processes external data from the GitHub API, which presents a surface for indirect prompt injection if the API response contains malicious instructions.
- Ingestion points: GitHub API responses in
get-org-metrics.sh,get-org-user-metrics.sh,get-enterprise-metrics.sh, andget-enterprise-user-metrics.sh. - Boundary markers: None present to distinguish data from instructions.
- Capability inventory: Network access and API interaction via the
ghCLI. - Sanitization: No sanitization or validation of the API response is performed before processing.
Audit Metadata