php-xxe-audit
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted PHP source code as part of its auditing workflow.
- Ingestion points: Local PHP source code files provided by the user for analysis.
- Boundary markers: The skill instructions do not define explicit boundary markers or delimiters to separate the instructions from the data (source code) being analyzed, nor do they instruct the agent to ignore embedded instructions within the code.
- Capability inventory: The skill has the capability to write audit reports to the local file system at
{output_path}/vuln_audit/xxe_{timestamp}.md. - Sanitization: There is no evidence of sanitization, escaping, or validation of the ingested source code content before it is processed by the agent.
Audit Metadata