sales-research
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from the web via WebSearch and WebFetch to generate CRM briefs. This creates an attack surface for indirect prompt injection where malicious instructions embedded in external websites could influence the agent's output.
- Ingestion points: Web search results and fetched page content used to populate CRM descriptions (SKILL.md).
- Boundary markers: The skill instructs the agent to label research as "AI-researched and unverified," which provides context to the user but does not provide technical isolation or explicit delimiters for the untrusted data.
- Capability inventory: The skill utilizes CRM write capabilities including mcp__zynkr__update_company and mcp__zynkr__create_task.
- Sanitization: There is no evidence of specific sanitization, escaping, or filtering applied to the fetched external content before it is processed or stored.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes an installation command that references a remote GitHub repository associated with the author's infrastructure.
- Evidence:
npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill sales-research
Audit Metadata