The Agent Skills Directory

[SAFE]: No malicious patterns, such as prompt injection, unauthorized data exfiltration, or persistence mechanisms, were detected. The skill correctly identifies its purpose as an interface for the 1sat-stack API and provides legitimate patterns for usage.
[DATA_EXFILTRATION]: The skill performs network operations to https://api.1sat.app/1sat, which is the official production API base described in the instructions. This behavior is consistent with the skill's purpose as a blockchain indexer client and does not involve the exfiltration of sensitive local data.
[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection because it ingests untrusted data from the blockchain.
Ingestion points: Data enters the context via the scripts/query-unified.ts script, which fetches transaction details, metadata, and inscription content from the 1sat-stack API.
Boundary markers: The demonstration script does not utilize explicit boundary markers or instructions for the agent to ignore potentially malicious content within the fetched data.
Capability inventory: The skill possesses the capability to perform network requests and process the results using the bun runtime environment.
Sanitization: The retrieved content is processed and logged without explicit sanitization or validation, creating a standard surface for indirect injection if the agent interprets the external content as instructional.

1sat-stack