hiring-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external platforms (LinkedIn and Apollo) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points:
linkedin_web_v2_search_jobs,linkedin_web_v2_job_detail,linkedin_web_v2_company_profile,apollo_company_job_postings, andapollo_company_search(SKILL.md, references/sandbase-api-map.md). - Boundary markers: None specified to delimit external content from system instructions.
- Capability inventory: Data retrieval and synthesis via
sandbase_call_tool. The skill is explicitly limited to read-only research (SKILL.md). - Sanitization: No explicit sanitization or filtering of the ingested external content is described.
Audit Metadata