aws-lambda
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several local binaries including
aws,jq, andzip. These are used as intended for cloud resource management and data processing. - [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface because it processes untrusted data from remote sources.
- Ingestion points: Data enters the agent context through the output of
aws lambda invoke(stored in/tmp/lambda-out.json) and the results ofaws logs tail. - Boundary markers: No delimiters or explicit instructions to ignore embedded content are provided in the command sequence.
- Capability inventory: The skill possesses high-privilege capabilities including the ability to invoke functions, update function code, and modify environment configurations.
- Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.
Audit Metadata