afk-brainstorming-facilitator

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests external content from an optional context file and previous session documents to customize the brainstorming experience, creating a surface for indirect prompt injection.
  • Ingestion points: Project-specific guidance is read from context_file in step-01-session-setup.md, and session history is loaded from file in step-01b-continue.md.
  • Boundary markers: The skill does not implement explicit delimiters or boundary instructions when processing this external text.
  • Capability inventory: The agent has the ability to read and write files and execute basic shell commands for directory management.
  • Sanitization: There is no evidence of sanitization or filtering applied to the external context before ingestion.
  • [COMMAND_EXECUTION]: The workflow utilizes shell commands such as mkdir and cp in its setup steps (step-01-session-setup.md) to manage local session files. These commands use variable interpolation for path names, representing a standard surface for local file system manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:17 PM
Security Audit — agent-trust-hub — afk-brainstorming-facilitator