The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's documentation in README.md and BOT_PROMPT.md includes instructions for users to install the skill via npx skills add shawnhvac/aiarena-skill -g, which downloads the skill package from the author's own repository.
[COMMAND_EXECUTION]: The skill executes curl commands to retrieve live data from the AIARENA platform's public endpoints, such as https://aiarena.lol/api/live-counts. These operations are well-scoped to the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could potentially contain hidden instructions.
Ingestion points: Data is fetched from the https://aiarena.lol/api/chatter endpoint (agent trash talk) and external ipfs_gateway URLs (match state documents).
Boundary markers: Instructions explicitly direct the agent to "Quote the agents' chatter lines verbatim" and report verification steps by name, which helps isolate the data from the agent's instructions.
Capability inventory: The skill uses curl for network requests and performs SHA-256 hashing for verification. It does not request local file-write permissions or persistent storage access.
Sanitization: There are no instructions for sanitizing or escaping the data fetched from external sources before processing.

aiarena