The Agent Skills Directory

[SAFE]: The skill primarily consists of instructional Markdown and templates for marketing workflows. Analysis of the skill files found no evidence of malicious intent or hidden code.
[COMMAND_EXECUTION]: The skill includes a Python script scripts/check-output.py designed to validate generated deliverables. The script uses standard libraries (re, sys, pathlib) to perform local file reads and basic text pattern matching. It does not execute external commands, perform network operations, or access sensitive system paths.
[EXTERNAL_DOWNLOADS]: Numerous links are provided to external documentation and expert playbooks. All identified URLs lead to well-known domains (e.g., lemlist.com, linkedin.com, youtube.com) or the author's own verified GitHub organization (LeadMagic). No obfuscated or suspicious URLs were found.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user-specific campaign context. Mandatory Evidence Chain: 1. Ingestion points: SKILL.md (processes user goals) and scripts/check-output.py (reads locally generated deliverables). 2. Boundary markers: Absent. 3. Capability inventory: Limited to local file reading; no network-send or file-write tools are provided. 4. Sanitization: Absent. Due to the lack of exploitable capabilities, this surface is assessed as safe.

lemlist-setup