expert-engine
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructional Markdown documents and references. It contains no Python code, Node.js scripts, or shell commands, ensuring no risk of malicious execution.
- [SAFE]: Analysis of all files, including 'SKILL.md' and the 'references/' directory, found no indicators of prompt injection, data exfiltration, or obfuscation.
- [SAFE]: The skill does not request or use any sensitive data, credentials, or system permissions.
- [SAFE]: Indirect prompt injection surface is considered safe. 1. Ingestion points: User problem statements are processed in Step 0 of 'SKILL.md'. 2. Boundary markers: Absent. 3. Capability inventory: No active capabilities such as subprocess calls or network operations were identified in the skill's own content. 4. Sanitization: Absent. The risk is negligible as the skill only performs cognitive analysis without performing external actions.
Audit Metadata