aws-sam-local-testing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python code snippets in
SKILL.mdthat usesubprocess.runto execute thesam local invokecommand, enabling the agent to trigger local Lambda function executions. - [INDIRECT_PROMPT_INJECTION]: The skill provides functionality to process and test Lambda functions using event payloads, which represents a potential injection surface.
- Ingestion points: Untrusted data can enter the agent context through event files (e.g.,
event.json) passed to thesam local invokecommand or through theeventparameter in theinvoke_lambdaPython function defined inSKILL.md. - Boundary markers: There are no explicit boundary markers or instructions provided to the agent to treat the contents of the event payloads as data rather than instructions.
- Capability inventory: The skill possesses the capability to execute shell commands via
subprocess.runand write to the local file system using shell redirection in the provided examples. - Sanitization: The documentation does not demonstrate sanitization or validation of the event payload content before it is processed by the local Lambda runtime.
Audit Metadata