aws-cloudwatch-logs
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell scripts that execute AWS CLI commands to perform log group discovery, metadata retrieval, and Insights query execution.
- Evidence includes calls to
aws logs describe-log-groups,aws logs start-query, andaws logs get-query-resultsthroughout SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from CloudWatch logs, which constitutes an attack surface where embedded instructions could attempt to influence the agent.
- Ingestion points: The
run_insights_queryfunction andaws logs get-query-resultscommand in SKILL.md fetch log content from AWS. - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious content within the log results.
- Capability inventory: The skill has the capability to execute further AWS CLI commands based on its analysis.
- Sanitization: There is no evident sanitization or filtering of the log data before it is presented to the agent for analysis.
Audit Metadata