dast-config

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed to analyze security configuration files. It uses a restricted set of tools (Read, Grep, Glob) and does not have network access, which mitigates risks associated with data exfiltration or unauthorized external communication.- [PROMPT_INJECTION]: The skill identifies an 'Indirect Prompt Injection' assessment surface because it processes untrusted external DAST configuration files.
  • Ingestion points: DAST configuration files (e.g., ZAP Automation Framework plans, Burp project files) and CI/CD workflow files (e.g., GitHub Actions, GitLab CI) located via Glob and Grep patterns.
  • Boundary markers: The skill includes a dedicated 'Prompt Injection Safety Notice' section that explicitly warns the agent to treat all file content as untrusted data and ignore embedded instructions.
  • Capability inventory: File access is restricted to the Read, Grep, and Glob tools as defined in the frontmatter. No subprocess execution, shell access, or network capabilities are enabled for this skill.
  • Sanitization: The instructions provide specific guidance to the agent to disregard URLs, scan rule descriptions, or alert messages that might resemble instructions or commands during the assessment process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:06 AM
Security Audit — agent-trust-hub — dast-config