sns

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): This skill defines surfaces for ingesting untrusted data through SNS message bodies and attributes.
  • Ingestion points: sns.publish() calls and subscriber endpoints (HTTP, Lambda, SQS) receive external content.
  • Boundary markers: None present in the code snippets; message bodies are processed as raw strings or JSON.
  • Capability inventory: Uses boto3 client for SNS publishing and aws sns CLI for resource management.
  • Sanitization: Code snippets do not demonstrate input sanitization or validation of message content before processing.
  • Command Execution (SAFE): The skill provides numerous AWS CLI commands for infrastructure management. These are consistent with the skill's primary purpose of AWS SNS administration and use standard documentation placeholders (e.g., account IDs and ARNs).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:54 PM