aws-sam-bootstrap

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides standard instructions for using the AWS SAM CLI, a well-known tool from a trusted vendor. It guides the user through legitimate serverless development tasks such as sam init, sam build, and sam deploy without any suspicious modifications.
  • [PROMPT_INJECTION]: The skill includes instructions to inspect and migrate existing Lambda functions and CloudFormation resources. This activity involves reading untrusted data (source code and templates) that could contain malicious instructions designed to influence the agent (Indirect Prompt Injection).
  • Ingestion points: Analysis of existing Lambda handlers, runtimes, and dependency layouts (SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading external project files.
  • Capability inventory: The skill uses Bash to execute sam commands and Read/Write tools for artifact generation (SKILL.md).
  • Sanitization: The skill does not describe any sanitization or validation logic for the content of the files it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:01 PM
Security Audit — agent-trust-hub — aws-sam-bootstrap