screenshot-feature-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: A comprehensive review of the skill's instructions and reference files reveals no malicious patterns, obfuscation, or safety risks.
- [DATA_EXFILTRATION]: The skill is designed to process user-provided screenshots and store the resulting feature analysis in the project's local directory (
docs/plans/). No network requests, external data transfers, or credential harvesting patterns were found. - [COMMAND_EXECUTION]: The skill utilizes a coordinated multi-agent architecture using the
Tasktool for sub-agent orchestration. It does not attempt to execute arbitrary shell commands, modify system configurations, or gain elevated privileges. - [PROMPT_INJECTION]: The instructions are clearly defined for feature extraction and do not include triggers intended to override model constraints, bypass safety filters, or leak system prompts.
Audit Metadata