create-second-brain-prd

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its processing of user-controlled requirement files.
  • Ingestion points: The skill reads the requirements file specified by the user in the first argument ($0) of the command.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate the untrusted content from the rest of the task logic.
  • Capability inventory: The agent is granted permission to perform web research on any tool or API listed in the file and to write the resulting PRD to the filesystem.
  • Sanitization: The workflow does not include any steps for sanitizing or validating the input data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 06:22 PM