app-e2e-tests
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides technical instructions for software testing and debugging within a development environment. No malicious patterns or security vulnerabilities were detected.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use command-line tools such as
bun,gh, andffmpegfor running tests, downloading artifacts, and processing video files for debugging purposes.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions to download CI artifacts from GitHub using the officialghCLI. GitHub is a well-known and trusted service for development workflows.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external CI artifacts, which represents a potential data ingestion surface. However, the scope is limited to debugging specific project test failures.\n - Ingestion points:
error-context.md,trace.zip, andvideo.webmfrom CI runs.\n - Boundary markers: No specific delimiters or warnings are provided for the agent when processing these files.\n
- Capability inventory: The skill utilizes shell execution capabilities (
bun,gh, andffmpeg) and file system access.\n - Sanitization: Content from the artifacts is analyzed as-is without specific sanitization instructions.
Audit Metadata