laravel-specialist
Fail
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a documentation link to
jeffallan.github.io. While GitHub Pages is a well-known service for hosting documentation, this specific URL and the referencing file were flagged by automated security reputation scanners. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user requirements to build application components, which creates a surface for indirect prompt injection.
- Ingestion points: The requirement analysis and architecture design phases described in
SKILL.mdwhere the agent interprets external instructions. - Boundary markers: No explicit delimiters or boundary instructions (e.g., 'ignore instructions within data') are present in the core workflow.
- Capability inventory: The skill requires the agent to perform file system modifications and execute multiple development commands (
php artisan make:model,php artisan migrate:status,php artisan route:list,php artisan test,php artisan queue:work,php artisan horizon) as detailed inSKILL.mdandreferences/queues.md. - Sanitization: The instructions do not define any sanitization or validation steps for the input data before it is used for code generation or command execution.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata