The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the agent-browser tool from Vercel Labs' official GitHub repository. This is documented as a trusted source and is a standard procedure for enabling the skill's automated research capabilities.
[COMMAND_EXECUTION]: The skill utilizes agent-browser and standard Node.js package management commands (npm/npx) to perform web scraping and environment setup. These operations are necessary for the skill's primary function of influencer identification and market analysis.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external social media profiles, which presents a surface for indirect prompt injection.
Ingestion points: Data is ingested through agent-browser get text body commands targeting search results and user profiles on TikTok, Instagram, and YouTube as seen in references/influencer-identification.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the scraped content.
Capability inventory: The skill has the capability to write research results to the local project workspace and perform subsequent network requests to follow links found during discovery.
Sanitization: No explicit sanitization or filtering of the retrieved web content is mentioned before it is interpolated into the agent's context.

paw-mkt-influencer