amplify-workflow
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests project files and has the capability to execute commands.
- Ingestion points: The skill reads local project files including
package.jsonand theamplify/directory to determine the project state. - Boundary markers: There are no explicit markers or instructions to treat data from the project files as untrusted content.
- Capability inventory: The skill executes local shell scripts, AWS CLI commands, and npm operations.
- Sanitization: The skill does not perform sanitization or validation of the ingested file content before it influences the agent's execution plan.
- [COMMAND_EXECUTION]: The skill executes a bundled shell script (
scripts/prereq-check.sh) to verify environment prerequisites and AWS credential status. It also relies on standard CLI tools such asnpmand theawsCLI to perform its primary development tasks.
Audit Metadata