legal-job-search
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could be used to influence the agent's behavior during resume and report generation.
- Ingestion points: The skill ingests Job Descriptions (JDs) provided by users (SKILL.md) and fetches company data, industry trends, and legal risk information through multiple rounds of Web Search (company-research-framework.md, firm-research-framework.md).
- Boundary markers: There are no explicit instructions or delimiters used to isolate external content or warn the agent to ignore embedded instructions within processed JDs or search results.
- Capability inventory: The skill has the ability to write local files (HTML resumes), generate Word documents using a 'docx' skill, perform OCR on user documents, and execute network searches.
- Sanitization: No evidence of sanitization, filtering, or validation is present for the data retrieved from web searches or external JD text before it is used to generate求职材料 (job search materials).
Audit Metadata