Security audit
Security checks for vulnerabilities and agentic risk
The Qwen integration is coherent, but its setup instructions allow an unverified remote installer to run without clear user approval.
Review and approve the CLI installation separately, including any bundled-skill synchronization, before allowing setup to run. Prefer a verified, fixed release. Submitted documents, images, audio, and text are processed through OOMOL and Qwen. The remote installer contents remain unverified; no malicious behavior was established.
The supplied command performs an Oomol CLI installation rather than a Qwen data operation. Nothing in the supplied chunk establishes this installation as a supporting dependency for Qwen, so its purpose and accessed resource are inconsistent with the declared description. The remote installer's contents are not supplied, so its further behavior cannot be assessed.
Piping a mutable remote script directly into Bash executes it without prior inspection, version pinning, or independent integrity verification. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent's local privileges; HTTPS alone does not protect against compromise of the script publisher.
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 workflow instructs the agent to execute actions with user-supplied payloads, but the safety guidance treats every untagged action as a safe read. Untagged actions include document analysis, OCR, and text translation, which transmit potentially sensitive content to Qwen through OOMOL; the file does not warn users about that disclosure.
The fallback directs an agent to install software after a missing-command error without first obtaining approval for local system changes. Both installation examples execute remotely supplied code, potentially exposing files and credentials accessible to the executing account; the conditional fallback limits exposure but does not establish installation authorization.
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