Security audit
Security checks for vulnerabilities and agentic risk
The skill treats uploading decrypted message attachments as a safe read, allowing private files to leave the messaging service without confirmation.
Before installing, require confirmation before decrypted attachments are uploaded and establish who can access file transit and how long files remain there. Use an inspected, verified CLI release and review its automatic skill synchronization. The bundled instructions were fully inspected, but external installers and server-side processing were not verified; no malicious intent was established.
The supplied chunk performs remote installer execution, not Weixin Bot data operations. Installation could be a supporting implementation detail if a dependency relationship were established, but none is shown here. The downloaded script is not supplied, so its further behavior cannot be determined.
The setup command pipes a mutable remote installer directly into a shell without verifying a pinned version, digest, or signature; the PowerShell alternative has the same execution pattern. Compromise of the distribution endpoint could therefore execute attacker-controlled code with the agent process's permissions, exposing local files and credentials. Conditional execution only when the CLI is absent reduces exposure frequency but does not establish installer integrity.
oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux
The download_media action decrypts message attachments and uploads them to file transit, yet its missing write tag places it under the instruction that untagged actions are reads safe to run directly. This can cause private attachment contents to be transferred to another storage service without the confirmation required for other state-changing actions; the action description discloses the upload but does not resolve the contradictory authorization guidance.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.
- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.
## Resources