symfony-security-auditor
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing several PHP packages via Composer, including a third-party auditor bundle (
vinceamstoutz/symfony-security-auditor) and various official Symfony AI platform bridges (symfony/ai-*). These are necessary for the tool's core functionality. - [COMMAND_EXECUTION]: Users are instructed to execute the security audit using the Symfony CLI (
bin/console audit:run). This command runs the installed package's logic to analyze local project source code. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the local project files it audits. Malicious instructions placed inside code comments or metadata in a project's source code could attempt to manipulate the LLM's auditing results.
- Ingestion points: Recursively scans project files including
.php,.twig,.yaml, and.xml. - Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to prevent the auditor from following embedded commands.
- Capability inventory: The tool executes local CLI commands and makes network requests to external AI model providers (Anthropic, OpenAI, Google, etc.).
- Sanitization: No specific sanitization or filtering of file content is described before it is processed by the AI models.
Audit Metadata