cloudformation-template-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Prompt Injection (SAFE): No override markers, role-play injections, or system prompt extraction patterns were detected.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials (API keys, tokens) or sensitive file paths (~/.aws/credentials, etc.) were found in the manifest.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not define any remote script downloads, package installations, or dynamic code execution patterns.
  • Command Execution (SAFE): While the skill is authorized to use Bash tools within the 'aws:*' namespace, this access is appropriate for its stated purpose as an AWS assistant and no malicious commands are pre-defined.
  • Indirect Prompt Injection (SAFE): The skill defines an attack surface for processing user templates but contains no logic to execute them unsafely. 1. Ingestion points: User-provided prompts and CloudFormation patterns. 2. Boundary markers: Absent. 3. Capability inventory: Read, Write, Edit, Bash(aws:*). 4. Sanitization: Not applicable as no executable scripts are included.
  • No Code (SAFE): The skill consists entirely of metadata (SKILL.md) and does not ship with any external scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM