goal-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized network activity detected.
- [DATA_EXPOSURE]: The skill reads health-related JSON files from the data-example directory. This access is appropriate for the skill's primary function of goal analysis and does not involve sensitive system files or credentials.
- [DYNAMIC_EXECUTION]: The skill creates HTML files containing JavaScript (ECharts) for data visualization. This is a standard visualization practice where the code is intended for rendering in the user's browser and does not affect the agent's execution environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external JSON logs, which represents a potential attack surface. 1. Ingestion points: health-goals-logs/*.json (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Read, Grep, Glob, Write. 4. Sanitization: Absent. Given the lack of command execution or network tools, the overall risk is minimal.
Audit Metadata