The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's installation instructions use npx skills add to fetch content from the GitHub repository DFectuoso/frontpage-sh-skills. This is a standard installation mechanism for the platform.
[COMMAND_EXECUTION]: The documentation includes executable command examples using curl, npx, and the mppx CLI tool for interacting with the API and performing payments.
[PROMPT_INJECTION]: The skill processes untrusted user-generated content retrieved from https://www.frontpage.sh/api/proposals, which includes fields like title, body, and suggesterName that could contain malicious instructions.
Ingestion points: Data enters the agent's context through the /api/proposals endpoint described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate user-submitted content from the agent's own instructional context.
Capability inventory: The skill has the capability to perform network POST requests (/api/votes, /api/proposals/submit, /api/comments) that trigger on-chain financial transactions ($0.01 USDC).
Sanitization: No specific text sanitization or verification of the external idea content is documented before the agent processes it.

frontpage-vote