The Agent Skills Directory

[SAFE]: The skill package is composed entirely of Markdown documentation and instructions. It defines workflows for role intake, search strategy, candidate mapping, and recruitment outreach without any automated or executable components.- [NO_CODE]: No Python scripts, Node.js packages, shell commands, or other executable files are present in the skill repository. The instructions are intended for the agent to follow purely as natural language guidance.- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external data such as candidate profiles from LinkedIn and GitHub to draft outreach. While this constitutes an ingestion point for untrusted data, the skill possesses no tools or capabilities (e.g., file writing, network requests, code execution) that could be leveraged for an attack. The ingestion points are public profile signals described in 'references/outreach_and_engagement_sequences.md', there are no specific boundary markers or sanitization steps defined, and the capability inventory is empty.

talent-sourcer