Security audit
Security checks for vulnerabilities and agentic risk
Review is recommended because setup executes an unverified download, and the required CLI has broader persistent effects than this skill explains.
Review and verify the CLI installation before allowing setup. If you do not want it to synchronize skills across agent homes, configure OO_SKILLS_SYNC_DISABLED=1 before invoking it, as documented in the [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Submit only text you intend OOMOL and StealthGPT to process. The bundled instructions were fully reviewed, but the remote installers and live connector code remain unverified.
The supplied command performs remote code execution for an apparent Oomol CLI installation, while the description promises StealthGPT data operations. Nothing in the chunk establishes this installation as a supporting dependency for StealthGPT. The downloaded script's contents and further effects are not provided.
The setup command streams a mutable remote script directly into Bash without verifying its integrity or reviewing it; the PowerShell alternative has the same execution pattern. A compromised installer endpoint or distribution pipeline could execute arbitrary code with the agent's local privileges and access local credentials or files. Conditional execution only when the CLI is missing reduces exposure frequency, not the consequences, although an enforced Bash(oo *) tool restriction may block these installation commands.
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 connector actions, including submitting text for AI detection or rewriting, without warning that the supplied content is sent through OOMOL to StealthGPT. Labeling untagged actions as safe to run directly overlooks the privacy impact of detect_ai_text, which can disclose user content even though it does not change account state.
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