The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it is designed to ingest and analyze untrusted external data.
Ingestion points: The agent reads PHP source code from the source_path and parses external markdown files (routes_{timestamp}.md and params_{timestamp}.md).
Boundary markers: The instructions do not define boundary markers or explicit safety instructions to prevent the agent from being influenced by malicious content or comments within the analyzed source code.
Capability inventory: The skill involves reading project files and writing structured trace reports to the output directory.
Sanitization: There are no instructions for sanitizing or escaping the content of the analyzed files before they are incorporated into the agent's context or output trace.
[NO_CODE]: The skill consists entirely of markdown-based instructions and does not include any accompanying scripts, binaries, or executable code.

php-route-tracer