Security audit
Security checks for vulnerabilities and agentic risk
This Winston AI integration needs review because it automatically runs an unverified installer and labels potentially paid content submissions as safe reads.
Review and verify the CLI installation separately before allowing automatic setup, including its effects on other agents' skills. Submit only content you intend OOMOL and Winston AI to process, and establish acceptable credit usage. The bundled skill was fully inspected, but the remote installer and exact downloaded CLI were not verified; no malicious payload was established.
The supplied command performs remote installation rather than Winston AI searching or reading. Nothing in the chunk establishes that this installer supports the declared functionality. The downloaded script is not provided, so its further behavior cannot be assessed.
The setup command pipes a remotely fetched, unpinned script directly into Bash without an independent integrity check or review; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint could therefore execute arbitrary code with the agent's local privileges, exposing accessible files and credentials, although the missing-CLI condition limits when this path is reached.
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 blanket rule that untagged actions are safe reads mischaracterizes analysis operations that submit text or URLs through OOMOL to Winston AI and may consume paid credits. An explicit request to analyze content with Winston AI normally authorizes that submission, but this rule can encourage sending additional sensitive material or incurring costs without recognizing those effects.
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