cold-email-playbook
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security risks were identified. The skill consists entirely of static markdown files used for informational reference and best practice guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill contains templates for email re-engagement that process external data via placeholders. 1. Ingestion points: Placeholders in
resources/re-engagement.mdsuch as{{their_reason}}and{{new_trigger_observed}}. 2. Boundary markers: The skill instructs the agent to use plain text and no links in first emails, but lacks formal delimiters for untrusted data. 3. Capability inventory: No file-write, network, or executable capabilities are present in this skill. 4. Sanitization: No explicit sanitization or filtering is defined for the placeholder content. - [COMMAND_EXECUTION]: The skill does not contain any scripts, shell commands, or tool definitions. All operations are restricted to reading local markdown files.
Audit Metadata