The Agent Skills Directory

EXTERNAL_DOWNLOADS (MEDIUM): The file rules/getting-started.md instructs users to execute npx @x402scan/mcp install. This command downloads and runs code from the @x402scan/mcp package on the npm registry. As the @x402scan organization is not a trusted source, this represents an unverifiable dependency installation that executes at runtime.
DATA_EXFILTRATION (LOW): The skill is designed to transmit search queries to enrichx402.com and retrieve sensitive PII, including names, phone numbers, and home addresses. While this is the skill's primary purpose, the transmission of data to an untrusted external domain carries inherent privacy risks.
INDIRECT_PROMPT_INJECTION (LOW): The skill ingests data from external API responses without clear sanitization, creating an attack surface for indirect prompt injection.
Ingestion points: Response data from x402.fetch calls to enrichx402.com.
Boundary markers: None identified in the skill instructions.
Capability inventory: Wallet management (x402.get_wallet_info), network access (x402.fetch), and integration with other enrichment skills.
Sanitization: No evidence of input validation or response sanitization.

people-property