afk-create-agent

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the afk command-line utility for managing agent catalogs and verifying setup configurations (e.g., afk show agents, afk setup agents). These commands are used for their intended purpose within the framework.
  • [EXTERNAL_DOWNLOADS]: Mentions the pi-subagents package as a dependency for the 'Pi' harness. The skill identifies the need for this package and instructs the user on how to install it via standard package managers if it is missing.
  • [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill ingests user-provided behavior descriptions, identities, and instructions to author new agent files (SKILL.md). 2. Boundary markers: Created agents follow a strict Markdown/YAML schema defined in references/portable-agent-schema.md which separates metadata from runtime instructions. 3. Capability inventory: The skill uses local shell execution for afk commands and file writing to author the portable agent files. 4. Sanitization: The skill validates agent names against a stable identity regex as specified in the schema reference.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:49 AM
Security Audit — agent-trust-hub — afk-create-agent