The Agent Skills Directory

[SAFE]: The skill provides legitimate technical instructions and boilerplate code for Hedera blockchain development. The instructions accurately reflect HIP (Hedera Improvement Proposal) standards for the Schedule Service.
[EXTERNAL_DOWNLOADS]: The skill references the @hashgraph/smart-contracts package and official Hashgraph GitHub repositories. These are well-known and authoritative sources for Hedera ecosystem development.
[PROMPT_INJECTION]: No patterns of instruction overrides, safety filter bypasses, or system prompt extraction were found. The instructional tone is standard for technical documentation.
[DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file access (e.g., .env, .ssh), or unauthorized data transmission was detected.
[INDIRECT_PROMPT_INJECTION]: The skill documents how to handle external callData for scheduling transactions. While this represents a data ingestion surface, the skill correctly advises on sanitization via return code validation and address checks. Following the mandatory evidence chain:
Ingestion points: callData and token parameters in Solidity snippets (SKILL.md).
Boundary markers: The skill highlights that system contract calls do not revert and requires developers to implement manual status checks.
Capability inventory: Writing scheduled transactions to the Hedera network via system contract address 0x16b.
Sanitization: Strong emphasis on checking rc == HederaResponseCodes.SUCCESS and validating the returned scheduleAddress to prevent silent failures.

hss-system-contract