skills/narasaka/skills/orchestrate/Gen Agent Trust Hub

orchestrate

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest task requirements from external sources (specifically Linear tickets) and use that data to brief delegate agents. This creates an attack surface where malicious instructions embedded in a ticket could influence the behavior of the orchestrator or its delegates.
  • Ingestion points: The 'Plan' section describes reading tasks and requirements from Linear tickets using the ticket tool.
  • Boundary markers: The instructions do not provide delimiters or warnings to the agent to ignore potential instructions embedded within the ingested ticket content.
  • Capability inventory: The skill has the capability to spawn new agent processes (delegate_task) and perform complex repository operations (gh-stack).
  • Sanitization: No sanitization or verification of the external ticket content is mentioned before the data is used to generate briefs for implementation delegates.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 04:02 AM