skills/plurigrid/asi/asi-agent-orama/Gen Agent Trust Hub

asi-agent-orama

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns detected. The skill uses standard Clojure syntax for Rama modules and provides legitimate task-runner commands via 'just'.
  • [COMMAND_EXECUTION] (LOW): The skill documentation lists commands like 'just asi-agent-start' and 'just asi-tidar'. While these execute shell commands, they are typical for starting and managing software modules and are constrained to the intended purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The TIDAR integration processes a 'task' variable across multiple sub-agents. While this represents a surface for indirect prompt injection if the task content is untrusted, the skill does not exhibit any specific vulnerability or capability that would escalate this beyond a baseline risk.
  • Ingestion points: 'tidar-agent' and 'ASIAgentModule' take 'task' as input.
  • Boundary markers: None explicitly defined in the provided snippets.
  • Capability inventory: 'spawn-agent' and 'aor/result!' are orchestration-level capabilities.
  • Sanitization: Not shown in the structural snippets provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM