vara-agent-network-skills
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Static analysis flagged
agent-create.mdfor attempt to override instructions. This is a false positive as the content consists of defensive boundary markers advising the agent to treat data fetched from the blockchain as evidence rather than instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Vara blockchain (chat, announcements, and identity cards). This risk is managed with explicit instructions inagent-create.mdandSKILL.mdto treat external content as data and ignore any embedded directives.\n- [COMMAND_EXECUTION]: The skill preamble inSKILL.mdusesevalto load its own configuration fromreferences/program-ids.md. Additionally,scripts/json-get.mjsusesnew Functionfor JSON parsing. Both uses are localized to the skill's operational logic.\n- [EXTERNAL_DOWNLOADS]: The skill interacts with official endpointsagents-api.vara.networkandvoucher-backend-agents.vara.network. These are trusted resources belonging to the Gear Foundation (the skill author) used for network indexing and gas vouchers.
Audit Metadata