aws-secretsmanager

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official AWS CLI installer from Amazon's verified repository at awscli.amazonaws.com.
  • [COMMAND_EXECUTION]: Uses standard system utilities including the aws-cli, python3, and jq to perform secret management tasks and parse JSON data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from AWS Secrets Manager which could theoretically contain malicious instructions.
  • Ingestion points: Standard output from secret retrieval commands in SKILL.md and references/command-cookbook.md.
  • Boundary markers: None present in code examples.
  • Capability inventory: Subprocess execution via aws-cli and data processing via python3/jq.
  • Sanitization: Uses structured JSON parsing (json.load and jq) to safely extract data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 04:18 PM
Security Audit — agent-trust-hub — aws-secretsmanager