enrich-with-aws-security-agent
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes findings from external logs that could potentially contain content influenced by an attacker.
- Ingestion points: The agent retrieves finding data from AWS CloudWatch Logs (as described in SKILL.md, Steps 2 and 3).
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the log data.
- Capability inventory: The skill is configured to use CloudWatch Logs tools to discover log groups and execute queries. It does not have general file-system or network access beyond these specific service tools.
- Sanitization: The skill does not explicitly describe a process for sanitizing or validating log content before it is presented to the user or used to explain incident behavior.
Audit Metadata