agent-debate

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an orchestrator for multi-agent debates, ingesting external inputs such as alternatives and evidence that could potentially contain malicious instructions.
  • Ingestion points: External data enters the agent context through the 'Decision' and 'Shared evidence' sections defined in references/debate_protocol.md and processed in SKILL.md workflow steps 1 and 3.
  • Boundary markers: The protocol utilizes structured Markdown templates (Decision frame, Synthesis frame) to delimit untrusted content from system instructions.
  • Capability inventory: The skill contains explicit prohibitions against high-risk actions. SKILL.md strictly forbids implementation, source code mutation, commits, merges, or direct writes to canonical memory during the debate process.
  • Sanitization: The workflow includes mandatory policy checkpoints before spawning reviewers and after each cycle, along with a human-in-the-loop requirement for any final decision or implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 12:01 PM
Security Audit — agent-trust-hub — agent-debate