confer

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local command-line interfaces for Claude and Codex. This is necessary for its primary function of model consultation. The implementation uses secure process spawning methods in scripts/confer.mjs that prevent shell injection by passing arguments in an array and using the '--' delimiter to isolate user-provided prompts from command flags.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it processes responses generated by external AI models. \n
  • Ingestion points: Responses from peer models are ingested via the claude and codex adapters in scripts/confer.mjs.\n
  • Boundary markers: Conversations are logged in markdown files with clear headers (e.g., '## R1 ← claude') to distinguish between different models and rounds.\n
  • Capability inventory: The host agent using the skill typically has broad system permissions.\n
  • Sanitization: The skill relies on the agent's internal safety filters and explicit markdown instructions in SKILL.md to evaluate external content safely and treat it as advisory.\n- [DATA_EXFILTRATION]: Conversation transcripts are stored in plaintext within the user's home directory (~/.confer/). The skill explicitly warns against including credentials or secrets in prompts to mitigate the risk of accidental exposure of sensitive information in these logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 12:25 PM
Security Audit — agent-trust-hub — confer