aws-ecs-monitor
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill utilizes shell scripts that execute system binaries like
aws,curl, andpython3. It constructs commands based on environment variables to monitor service health and retrieve logs, which is a standard but privileged operation for infrastructure tools. - [PROMPT_INJECTION] (LOW): There is a potential for Indirect Prompt Injection through application logs. 1. Ingestion points: Untrusted data enters the context via
aws logs filter-log-events(referenced inscripts/cloudwatch-logs.sh). 2. Boundary markers: The documentation does not specify any delimiters or instructions to ignore embedded prompts in logs. 3. Capability inventory: The skill can perform AWS API calls, write to the local filesystem (e.g.,./data/), and make network requests viacurl. 4. Sanitization: No sanitization or escaping of log content is mentioned; the scripts perform pattern matching to categorize errors.
Audit Metadata