ui-code-auditor
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and resources focus exclusively on static analysis of source code. No indicators of malicious intent, such as credential harvesting, unauthorized network connections, or persistence mechanisms, were found. Commands such as '/majestic:config' are consistent with the vendor's own configuration tools.
- [PROMPT_INJECTION]: Analysis of the skill's data processing reveals an indirect prompt injection surface.
- Ingestion points: Step 4 of the audit process in 'SKILL.md' reads content from various local UI files (e.g., .tsx, .jsx, .erb, .css) to perform analysis.
- Boundary markers: The instructions do not specify the use of delimiters or specific instructions to the agent to disregard natural language instructions found within the audited code.
- Capability inventory: The skill is granted access to the 'Bash', 'Read', 'Grep', and 'Glob' tools to locate and inspect files.
- Sanitization: External source code content is processed in its raw form to apply the audit patterns.
- Assessment: This surface is an inherent characteristic of the skill's primary function (code auditing) and is documented as a risk factor rather than a security vulnerability.
Audit Metadata