php-cmd-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs static analysis on external PHP source code, which serves as a potential vector for indirect prompt injection.
- Ingestion points: Untrusted source code files from the PHP project being audited.
- Boundary markers: The instructions lack specific delimiters or isolation rules for the code content, allowing potential instructions hidden in comments or strings to influence the agent's reasoning.
- Capability inventory: The agent is authorized to read project files, write detailed audit reports (including PoCs) to the local file system, and invoke external analysis capabilities such as
php-route-tracer. - Sanitization: No explicit sanitization, filtering, or validation is performed on the content of the files before the agent processes and interprets them.
Audit Metadata