scheduled-report-refresh
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a legitimate workflow for data analysis and reporting using Amplitude-specific tools such as use_amp_dashboards and get_amplitude_charts. No malicious commands or safety bypasses were found.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface for processing external Amplitude dashboard data. 1. Ingestion points: Data is retrieved from Amplitude dashboards via the get_amplitude_charts tool (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill is limited to summarizing data and generating report tables; it lacks dangerous capabilities such as file system writes or arbitrary command execution. 4. Sanitization: None specified. The risk is minimized as the ingestion is required for the skill's primary analytical purpose.
Audit Metadata