jd-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Job Description (JD) text provided by users, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill is designed to ingest and process raw JD text from users to extract information and perform matching, as documented in the '触发条件' (Trigger Conditions) and '工作流程' (Workflow) sections.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to treat the input JD text strictly as data, which may allow embedded malicious instructions to be executed by the agent.
- Capability inventory: The skill possesses significant capabilities via the
ReadandWritetools, including reading the user's base resume atdata/resume/base.jsonand writing structured analysis todata/companies/{company}.json. - Sanitization: No evidence of sanitization, validation, or filtering of the external JD content is present in the skill's logic or patterns.
Audit Metadata