animated-chart
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions explicitly direct the agent to stop and notify the user before installing any new software or dependencies, ensuring human oversight for environment changes.
- [SAFE]: The skill does not attempt to access sensitive files, hardcode credentials, or perform network operations. It uses local HTML generation and system tools for media processing.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user (such as chart titles and values) to populate generated HTML.
- Ingestion points: User-provided inputs for [TITLE], [LABEL], and [VALUE] in SKILL.md.
- Boundary markers: Square brackets act as placeholders for user data.
- Capability inventory: The agent can generate code (HTML), take screenshots, and execute local media conversion tools.
- Sanitization: No specific sanitization or escaping of the user-provided data is mandated in the instructions.
- [SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were detected in the instructions or metadata.
Audit Metadata