coding-with-plan
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs agents to process various external files, creating a vulnerability surface where malicious instructions could be embedded in data.
- Ingestion points: According to the "输入与启动" section in
SKILL.md, the agent loads theplanfile,AGENTS.md,CONTEXT-MAP.md,CONTEXT.md, and other project-specific development and test documentation. - Boundary markers: There are no instructions for the agent to use specific delimiters or boundary markers when reading these external files, increasing the risk of the model confusing data with instructions.
- Capability inventory: The skill environment includes powerful orchestration capabilities such as
spawn_agent,followup_task,send_message,wait_agent,list_agents, andinterrupt_agent. Additionally, the created sub-agents are expected to perform file modifications and execute code for testing. - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content of the external files being processed.
Audit Metadata