Skills
skills/catoncat/codex-transcript-md/export-session/Gen Agent Trust Hub

export-session

Fail

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses npx -y @act0r/codex-transcript-md to download and execute code from an external npm package at runtime. This package is not from a known trusted source or the skill author's verified namespace, making its contents unverifiable.
  • [COMMAND_EXECUTION]: The skill executes shell commands with user-provided session IDs or file paths as arguments. This pattern could be exploited for command injection if the input is not strictly validated before being passed to the shell.
  • [DATA_EXFILTRATION]: The skill is designed to read sensitive session transcripts stored in local directories like ~/.codex/sessions. It includes a feature to upload this data to 0g.hk, a public file-sharing service, which could lead to sensitive information leakage.
  • [DATA_EXFILTRATION]: The skill accesses potentially sensitive file paths such as %USERPROFILE%\.codex\sessions and ~/.codex/sessions to read conversation history.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 14, 2026, 03:56 PM
Security Audit — agent-trust-hub — export-session