performance-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script
youtube.pylocated within the plugin's root directory to fetch campaign-specific video metrics. This is a standard integration for retrieving platform data. - [SAFE]: The skill manages campaign analyses by writing to the
memory/directory, adhering to established conventions for agent persistence and state management. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources including platform exports and influencer reports. While this presents an ingestion surface, it is necessary for the skill's primary analytical purpose.
- Ingestion points: Influencer reports, platform exports, and analytics screenshots processed during campaign data gathering (Step 1).
- Boundary markers: None explicitly defined in the prompts.
- Capability inventory: File system writes to
memory/and execution of the localyoutube.pyconnector script. - Sanitization: Content is used for metric aggregation and qualitative reporting without further execution.
Audit Metadata