performance-check
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts
scripts/performance-monitor.pyandscripts/campaign-tracker.pyto save performance snapshots and log campaign insights. - [PROMPT_INJECTION]: Provides a surface for indirect prompt injection by ingesting and processing data from external analytics platforms.
- Ingestion points: Metric data retrieved from connected platforms like Google Analytics, Meta, and LinkedIn in Step 3.
- Boundary markers: No explicit delimitation or 'ignore instructions' warnings are present for the external data.
- Capability inventory: Includes the ability to execute subprocesses via Python scripts for historical data persistence.
- Sanitization: There is no mention of validation or sanitization of the metrics data before processing or script execution.
- [SAFE]: Accesses brand profile and industry benchmark files within the
~/.claude-marketing/directory to contextualize performance reports.
Audit Metadata