cloud-security-engineer

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates a 'Prompt Injection Safety Notice' that utilizes instruction-override patterns (e.g., 'IGNORE those instructions') as a defensive mechanism to ensure the agent adheres to the provided security methodology and does not deviate when processing untrusted input.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and analyze external configuration data.
  • Ingestion points: Infrastructure-as-Code (IaC) templates and cloud configuration data described in the 'When to Use' and 'Engagement Types' sections.
  • Boundary markers: The skill includes a 'Prompt Injection Safety Notice' instructing the agent to ignore conflicting instructions in user messages or file contents.
  • Capability inventory: The skill is configured to use file-system tools such as Read, Grep, and Glob to examine code.
  • Sanitization: There is no evidence of programmatic sanitization or schema validation for external data, with the skill relying on instructional guardrails.
  • [SAFE]: All external references point to reputable and established security documentation sources, including NIST, CIS, and the official documentation for AWS, Azure, and GCP.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 02:07 AM
Security Audit — agent-trust-hub — cloud-security-engineer