add-experience
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to update professional materials, creating a potential attack surface.
- Ingestion points: User input provided via "自由文本" (free text) or "结构化描述" (structured descriptions) is parsed in Step 1 and used to populate project experience files.
- Boundary markers: The instructions do not define boundary markers or explicit instructions for the agent to ignore or sanitize embedded commands within the user's project descriptions.
- Capability inventory: The skill has capabilities to read, write, and create files and directories within the
materials/path, includingtimeline.md,core-projects.md, andbase-resume.md(via Step 4). - Sanitization: There is no mention of sanitizing or escaping the user-provided text before it is interpolated into the markdown files.
Audit Metadata