stacking-delegation
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external API, creating a surface for indirect prompt injection.
- Ingestion points: Data is fetched from Hiro API endpoints (
api.hiro.so) for PoX cycle status, address balances, and rewards instacking-delegation.ts. - Boundary markers: The skill returns structured JSON output to the agent, providing clear separation between data and control logic.
- Capability inventory: The skill is capable of performing network fetches and executing local commands via
Bun.spawnSyncfor dependency management. - Sanitization: The script parses incoming JSON and extracts specific keys for processing, preventing the direct passing of raw external strings to the agent without structure.
- [COMMAND_EXECUTION]: The
install-packscommand usesBun.spawnSyncto runbun add commander. This is a standard and transparent method for ensuring the required command-line interface dependency is installed.
Audit Metadata