The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a managed indirect prompt injection surface because it processes untrusted inputs from CRM records and user data.
Ingestion points: Data is ingested through inputs like person_to_introduce and reason, plus get_contact and get_deal actions.
Boundary markers: No specific delimiters or safety instructions are used to separate external content.
Capability inventory: The skill uses email for drafting and crm for reading data.
Sanitization: Mitigation is provided by the approval_required: true configuration, ensuring human oversight.
[NO_CODE]: No executable code is provided with this skill.
[SAFE]: All identified actions and data access patterns align with the skill's stated purpose and use authorized platform tools.

Warm Intro Drafter