onboard

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary data from an "unfamiliar codebase," which serves as a significant attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read documentation (README, CONTRIBUTING), configuration files (package.json, .env.example), and source code files throughout the project.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the codebase files.
  • Capability inventory: The skill utilizes file system reading, directory traversal, git log execution, and shell command execution for builds and tests.
  • Sanitization: No sanitization or validation of the codebase content is performed before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute build and test scripts (Step 6). Since these commands are typically defined within the target codebase's configuration (like package.json scripts or Makefiles), this allows for the execution of arbitrary shell commands defined by an external, potentially untrusted source.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:19 PM
Security Audit — agent-trust-hub — onboard