The Agent Skills Directory

[SAFE]: The skill facilitates legitimate professional development and research tasks by helping users define archetypes, tier contacts by reachability, and design effective interview questions based on established productivity frameworks.- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its reliance on external data.
Ingestion points: The skill ingests data from local markdown files (lifestyle-design.md, dreamline.md) and performs web searches to find individuals across platforms like LinkedIn, Twitter, and niche communities.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the profiles or pages discovered during search.
Capability inventory: The skill utilizes web search tools and performs file-writing operations to record research results.
Sanitization: No explicit sanitization or validation of the ingested external content is performed before the data is presented to the user or used for synthesis.

expert-research