php-expr-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PHP source code, which provides a potential vector for indirect prompt injection if the analyzed files contain adversarial instructions designed to mislead the AI auditor.
- Ingestion points: PHP source code files read by the agent during the audit process.
- Boundary markers: The skill lacks instructions for the agent to use explicit delimiters or specific guardrails to ignore instructions found within the code being analyzed.
- Capability inventory: The agent utilizes searching tools like
rg(ripgrep) and generates vulnerability reports in markdown format. - Sanitization: There are no specified procedures for sanitizing or escaping the content of the source code before it is analyzed by the agent.
Audit Metadata