php-vuln-scanner

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 external data from project files such as composer.json, composer.lock, and generated route reports (routes_{timestamp}.md). If these files contain malicious instructions, the agent might follow them during the analysis phase.
  • Ingestion points: The skill reads project source code, dependency manifests (composer.lock), and external analysis data (routes_{timestamp}.md, params_{timestamp}.md).
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to treat the content of these external files as untrusted data.
  • Capability inventory: The skill describes operations for reading files and generating structured markdown reports. No dangerous capabilities like direct shell execution or network exfiltration are explicitly invoked in the instructions.
  • Sanitization: There are no explicit instructions to sanitize or validate the content extracted from the dependency files or route maps before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:59 AM
Security Audit — agent-trust-hub — php-vuln-scanner