atmos-aws-security

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions intended to manipulate the agent's output or the generated infrastructure code.
  • Ingestion points: According to the 'Context You Receive' section in SKILL.md, the skill ingests Finding details (specifically titles and descriptions) and Component source code from external sources.
  • Boundary markers: The skill instructions do not specify any delimiters or safety markers to differentiate between the agent's instructions and the potentially untrusted data being analyzed.
  • Capability inventory: The skill is designed to generate sensitive infrastructure artifacts, including Terraform HCL changes, stack configuration (YAML), and deployment commands (atmos terraform apply).
  • Sanitization: There is no evidence of input validation or sanitization to prevent malicious content within a security finding from influencing the remediation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 12:22 PM
Security Audit — agent-trust-hub — atmos-aws-security