The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Stacks blockchain during name lookups and info queries, which could potentially contain malicious instructions.
Ingestion points: lookup, reverse-lookup, and get-info commands in bns/bns.ts.
Boundary markers: Data is returned as structured JSON, but no explicit delimiters are used to isolate instructions.
Capability inventory: The skill can execute wallet transactions through claim-fast, preorder, and register.
Sanitization: No specific sanitization for AI instruction patterns is applied to blockchain-retrieved strings.

bns