ddd-qa-chain
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands mapped from the project's local infrastructure. It specifically assembles sequences of commands (e.g.,
<L1 命令> && <L2 命令>) for execution within the terminal to verify different quality layers (Unit, Contract, E2E, etc.). - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it identifies its execution targets by parsing external project files that could be modified by third parties.
- Ingestion points: Probing
package.jsonscripts, GitHub Actions/CI configuration files, and directory layouts to determine test runners. - Boundary markers: None identified; the skill maps detected strings directly into shell command templates.
- Capability inventory: The skill possesses the capability to execute arbitrary shell commands via the agent's terminal based on the results of its project mapping phase.
- Sanitization: Absent; the skill does not specify validation or sanitization for the command strings it identifies before executing them.
Audit Metadata