p9
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an orchestrator that ingests user project requirements to generate "Task Prompts" for a team of downstream agents ("P8 team"). This multi-step instruction chain creates a vulnerability surface where malicious user input could potentially influence the behavior of the agents receiving the generated prompts.
- Ingestion points: Processes user input when triggered by keywords like 'P9模式', 'tech-lead', or '帮我管理这个项目' in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings to protect downstream agents from malicious content within the user-provided project data.
- Capability inventory: The skill generates prompts that coordinate multiple parallel agents and manages project task breakdowns.
- Sanitization: There are no instructions for validating, escaping, or filtering user-provided content before it is interpolated into the prompts sent to other agents.
Audit Metadata