php-route-tracer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of PHP source code and route metadata to generate its tracing reports. This creates a surface for indirect prompt injection if an attacker embeds malicious instructions within comments, strings, or metadata of the code being analyzed.
- Ingestion points: The tool reads from the user-provided source_path, route definition files (routes_{timestamp}.md), and parameter structures (params_{timestamp}.md).
- Boundary markers: The skill mandates the use of highly structured markdown templates, mandatory tables, and specific evidence checklists, which serves as a delimiter for the AI's output and helps maintain the intended behavior.
- Capability inventory: The skill facilitates reading from the filesystem and writing reports to an output directory. It does not have access to network tools or arbitrary code execution capabilities.
- Sanitization: There are no explicit instructions for the AI to sanitize or escape untrusted content extracted from the source code before it is included in the output report's evidence sections.
Audit Metadata