crm-enrichment
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines an enrichment workflow that processes external data, creating an inherent surface for indirect prompt injection.\n
- Ingestion points: The agent is instructed to fetch data from LinkedIn profiles, Companies House, news articles, and job postings (SKILL.md).\n
- Boundary markers: The skill does not provide instructions for delimiters or techniques to isolate external data from internal instructions.\n
- Capability inventory: The agent is tasked with updating CRM records, triggering lead re-scoring, and flagging records for review (SKILL.md).\n
- Sanitization: No data validation or sanitization procedures are specified for the information gathered from external sources.\n- [NO_CODE]: The skill consists entirely of instructional markdown and evaluation data. No executable scripts, binaries, or package dependencies were found.
Audit Metadata