chart-data-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for an AI agent to perform visual data extraction. No malicious patterns, command execution, or unauthorized network requests were found in the instructions.- [NO_CODE]: This skill contains no executable scripts (Python, Node.js, Shell) or configuration files that trigger code execution. All logic is handled via the agent's reasoning capabilities.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of chart images, which represents a potential attack surface.
- Ingestion points: The skill primarily ingests user-uploaded chart images (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential text-based commands embedded within images.
- Capability inventory: The skill does not request any tools (e.g., shell, filesystem, or network access) in its frontmatter or body, which significantly mitigates the risk of an injection being used to perform unauthorized actions.
- Sanitization: No input sanitization or validation logic is present for the image data being processed.
Audit Metadata