forewrite

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script to read from and write to a local state file located at ~/.forewrite/graph.json. This is used exclusively for maintaining a history of user evaluations and does not execute arbitrary shell commands or external code.
  • [DATA_EXPOSURE]: The skill accesses the local file system to store user-provided project ideas and evaluation results. This data is stored in a hidden directory in the user's home folder (~/.forewrite/). No credentials or sensitive system files are accessed.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted user input describing project ideas and future scenes. While it accepts external data via 'forewrite-ingest' JSON blocks, it treats this data as structured records for storage rather than instructions to be executed, minimizing the risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 12:31 PM