notification-licenciement-selim-brihi
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides a valid workflow for drafting legal notifications using local reference materials.
- [SAFE]: The skill exhibits an indirect prompt injection surface as it processes user-provided information (company, employee, and grievance details) to generate a document. Ingestion points: Phase 1 information collection in SKILL.md. Boundary markers: No specific delimiters or safety instructions are used for user-provided text interpolation. Capability inventory: Uses docx tool for file creation and view for reading reference files. Sanitization: No explicit sanitization of user input is implemented. This surface is considered inherent to the skill's primary function and no malicious exploitation patterns were found.
- [SAFE]: All references and templates are stored locally (references/mentions-obligatoires.md and references/exemples-griefs.md), eliminating risks associated with external downloads or remote code execution.
- [SAFE]: No evidence of credential harvesting, data exfiltration, obfuscation, or persistence mechanisms was found in the skill body or its associated reference files.
Audit Metadata