nazim-help-articles
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers the execution of
php artisan db:seed --class=HelpCenterArticleSeederto update the application's database after generating help articles. This is a standard administrative task within the Laravel framework context for which the skill is designed. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it reads and processes data from external files (frontend code and manifests) that could contain malicious instructions.
- Ingestion points: The agent reads content from
backend/resources/help-center/MANIFEST.md, frontend page components, and TypeScript hooks (use{Resource}*.tsx). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the content being documented and its operational instructions.
- Capability inventory: The skill has the ability to read and write files within the project directory and execute shell commands via the PHP Artisan CLI.
- Sanitization: There is no evidence of content sanitization or validation before the agent incorporates information from the source code into its output or database operations.
Audit Metadata