skills/b-open-io/1sat-sdk/stack-api/Gen Agent Trust Hub

stack-api

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted, user-generated data sourced from the BSV blockchain via the indexing API.
  • Ingestion points: Untrusted data enters the agent context through several endpoints defined in SKILL.md and references/api-reference.md, specifically /content/{outpoint}, /ordfs/metadata, and /bap/profile/{bapId}.
  • Boundary markers: There are no explicit instructions or delimiters in SKILL.md to distinguish between system-provided API documentation and the raw data retrieved from the blockchain.
  • Capability inventory: The skill is designed to fetch and display blockchain content. The example script scripts/query-unified.ts includes functionality to fetch inscription content and output it to the terminal, which could contain malicious prompts embedded by third-party blockchain users.
  • Sanitization: The provided documentation and scripts do not include sanitization or filtering logic for content retrieved from external API calls before it is presented to the agent or the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 03:07 PM
Security Audit — agent-trust-hub — stack-api