atmos-aws-security
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown intended to guide an AI agent's behavior and does not contain scripts, executables, or network-enabled code.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. 1. Ingestion points: The agent processes AWS finding details, resource ARNs, and component source code from the environment. 2. Boundary markers: The prompt does not define explicit delimiters to separate untrusted context from instructions. 3. Capability inventory: The skill specifies the generation of shell commands (atmos terraform apply) and configuration changes. 4. Sanitization: No sanitization of the input data is described. This is a common characteristic of analysis assistants.
- [NO_CODE]: No scripts or executable files are included in the skill package.
Audit Metadata