character-management

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a specialized CLI utility (story) or a bundled Node.js script (../story-maintenance/scripts/story.js) to perform project maintenance tasks. These commands include story reindex, story wordcount, story check, and story diagram. These are standard development tools for the story-management ecosystem and operate on local files within the project directory.
  • [REMOTE_CODE_EXECUTION]: No remote code execution was detected. The skill specifically instructs the agent to use Node.js rather than Bun or package scripts to avoid loading untrusted local configuration files (bunfig.toml, .env) that might contain execution hooks.
  • [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were identified. All character management is performed on the local filesystem within the characters/ directory.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system instructions. It uses "IMPORTANT" only in the context of standard instructional logic.
  • [OBFUSCATION]: No obfuscated code, Base64 strings, or hidden characters were detected in any of the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 02:47 AM