cn-soe-interview
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external text such as recruitment notices (招聘公告) and candidate backgrounds. This creates a surface where malicious instructions embedded in the source documents could influence the agent's behavior. However, the skill lacks access to sensitive tools or the ability to perform actions beyond generating text responses, which significantly limits the potential impact.
- Ingestion points: User-provided recruitment notices and offer details in SKILL.md.
- Boundary markers: None mentioned.
- Capability inventory: Text generation only; no file system, network, or subprocess access is requested or used.
- Sanitization: Not explicitly defined in the prompt instructions.
- [NO_CODE]: The skill consists only of markdown instructions and does not include any executable scripts, configuration files, or external code dependencies.
Audit Metadata