cold-email-personalization
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed strictly of Markdown instructions and templates. It does not include any executable scripts, binaries, or configuration files that grant system permissions.
- [INDIRECT_PROMPT_INJECTION]: The methodology encourages the agent to research and scrape data from external, untrusted sources such as prospect websites, social media profiles, and online reviews to personalize outreach content.
- Ingestion points: Research data collected from third-party websites and LinkedIn posts as described in assets/research-playbook.md.
- Boundary markers: None identified; the agent is instructed to use scraped information to directly populate variables in email templates.
- Capability inventory: The agent uses external information to generate natural language email drafts and creative selling points (assets/creative-ideas.md).
- Sanitization: No instructions are provided to sanitize or validate the external data for embedded malicious prompts before it is processed by the agent.
Audit Metadata