php-sql-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically PHP project source code and route mapping files.
- Ingestion points: The skill reads external files such as
routes_{timestamp}.md,params_{timestamp}.md, and PHP project source code to perform its audit. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing the source code, which could allow maliciously crafted code comments or strings to influence the agent's behavior.
- Capability inventory: The skill has the capability to read project files, invoke the
php-route-tracertool, and write detailed vulnerability reports to the file system. - Sanitization: There are no instructions for sanitizing or escaping the content of the audited source code before it is interpolated into the final markdown report segments, such as the data flow chain or PoC sections.
Audit Metadata