The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines a command-line interface with several subcommands (post, read-feed, search-tags, get-profile, set-profile, get-pubkey, relay-list, amplify-signal, amplify-text) meant to be executed via bun run as seen in SKILL.md and nostr.ts.
[DATA_EXFILTRATION]: The skill performs network operations to communicate with Nostr relays (e.g., wss://relay.damus.io, wss://nos.lol) and fetches data from an external API at https://1btc-news-api.p-d07.workers.dev/takes/ in nostr.ts.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could be used to influence agent behavior.
Ingestion points: External data is ingested from Nostr relays in the read-feed, search-tags, and get-profile commands, and from a third-party API in the amplify-signal command in nostr.ts.
Boundary markers: There are no boundary markers or instructions to the agent to ignore embedded commands within the ingested data.
Capability inventory: The skill has the capability to write to the Nostr network via the post, set-profile, amplify-signal, and amplify-text subcommands.
Sanitization: No sanitization or filtering is performed on the ingested content before it is passed back to the agent context.

nostr