afk-profile-use

Warn

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the afk CLI tool, specifically afk skills profiles use <profile> and afk skills get <skill>. This allows the agent to interact directly with the host system's shell environment.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching instructions from an external tool and applying them to the current session without sanitization.
  • Ingestion points: External skill instructions are ingested via the afk skills get <skill> command as defined in SKILL.md.
  • Boundary markers: None; instructions are applied directly to the agent's context.
  • Capability inventory: The skill has the capability to execute shell commands and modify the agent's instruction set at runtime.
  • Sanitization: There is no evidence of validation or filtering of the instructions returned by the afk tool before they are applied.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 29, 2026, 04:44 AM
Security Audit — agent-trust-hub — afk-profile-use