aws-security

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution Patterns]: The skill is built around the execution of AWS CLI commands to audit services like GuardDuty, Inspector, and Security Hub. These patterns are used for read-only data retrieval and configuration review, which is consistent with the skill's auditing objectives.
  • [Indirect Prompt Injection Surface]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from security findings.
  • Ingestion points: Data enters the context via the output of AWS CLI commands like aws guardduty get-findings and aws securityhub get-findings-v2 as described in the findings-related reference files.
  • Boundary markers: The skill includes instructions to present summaries first and avoid severity judgments (e.g., in SKILL.md Global Rules), although it lacks explicit delimiters for the ingested data.
  • Capability inventory: The agent's capabilities are restricted to non-mutating AWS CLI operations across all referenced services.
  • Sanitization: No explicit sanitization or filtering of the external finding content is defined within the provided procedures.
  • [Sensitive Data Management]: The skill provides guidance on identifying and handling sensitive information like account IDs and IP addresses. It instructs the agent to prioritize summaries and verify data handling policies, which serves as a security-conscious approach to data presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 08:08 AM