trust-center

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes a deployment script (deploy.sh) and uses the AWS CLI to manage CloudFormation stacks, package Lambda handlers, and synchronize assets to S3. These operations are core to the skill's purpose of automating cloud infrastructure provisioning.
  • [EXTERNAL_DOWNLOADS]: During the build phase, the skill executes npm install to download standard React dependencies from the official NPM registry. It also references and provides integration guides for well-known e-signature services including DocuSign, Documenso, OpenSign, and DocuSeal.
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection in SKILL.md (Step 2), where it parses user-uploaded compliance documents (e.g., SOC 2 reports) to extract audit metadata. It lacks explicit sanitization or boundary markers for the extracted content, which is used to pre-fill configuration data and database entries. The skill's capabilities include shell command execution and authenticated AWS resource management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:07 AM
Security Audit — agent-trust-hub — trust-center