crm-enrichment
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting data from external sources (LinkedIn profiles, posts, news articles, and job postings) to update internal CRM records.
- Ingestion points: Processes information retrieved from LinkedIn profiles and activity, public news articles, and hiring signals found in job postings (SKILL.md).
- Boundary markers: No explicit technical delimiters or boundary instructions are provided to isolate untrusted external content from the agent's instructions, though logical safety rules for data integrity are present.
- Capability inventory: The workflow allows the agent to modify CRM fields, trigger lead re-scoring, and generate alerts for sales representatives based on external data.
- Sanitization: The instructions include process-level verification steps, such as checking email deliverability and cross-referencing company details with official registries.
Audit Metadata