php-tpl-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 PHP source code, which creates a potential surface for indirect prompt injection if the code contains instructions disguised as comments or strings.
- Ingestion points: PHP source code files within the project directory.
- Boundary markers: None explicitly defined in the instructions to separate code data from agent instructions.
- Capability inventory: The skill has the capability to read local files and write audit reports to the filesystem (
{output_path}/vuln_audit/tpl_{timestamp}.md). - Sanitization: The skill does not specify sanitization or escaping mechanisms for the analyzed content before it is processed by the agent.
Audit Metadata