wiki-researcher
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides guidelines for technical analysis and does not contain any malicious patterns, commands, or network operations.
- [NO_CODE]: The skill is composed entirely of instructional text and metadata, with no scripts or executable logic.
- [SAFE]: Indirect prompt injection surface: 1. Ingestion points: The skill is designed to analyze arbitrary user-provided codebase files (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed code are present. 3. Capability inventory: No high-risk capabilities such as network access, file writing, or subprocess execution are defined within this skill. 4. Sanitization: No sanitization or escaping of analyzed content is specified. This represents a standard surface for research tools and contains no active threats.
Audit Metadata