Security audit
Security checks for vulnerabilities and agentic risk
The Dandelion integration fits its purpose, but its setup can execute unchecked downloaded code and introduce broader agent-skill changes without clearly explaining them.
Review and install a verified CLI release yourself before enabling automatic setup. Check its startup skill-synchronization controls and approve broader agent-skill changes. Submit only text you intend OOMOL and Dandelion to process. The complete bundled artifact was inspected, but the external installers and exact CLI runtime effects remain unverified.
The supplied command does not search or read Dandelion data. It executes an external installer from cli.oomol.com, and the supplied content establishes no connection between that installation and the declared Dandelion functionality. The installer's contents and further effects are not visible in this chunk.
The supplied code performs only an authentication action, rather than the declared Dandelion search or read operations. Authentication could support API access, but this chunk provides no evidence that oo authenticates to Dandelion or implements the described functionality.
The fallback installation command executes a mutable remote script directly in a shell without a pinned version or integrity verification; the PowerShell alternative has the same weakness. Although this is a legitimate CLI setup path triggered only when the tool is missing, compromise of the script distribution channel could execute attacker-controlled code with the agent process's permissions.
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 submit action payloads through OOMOL to Dandelion, including text supplied for analysis. Although the API integration is identified, there is no warning that potentially sensitive text leaves the user's environment, and line 47 treats all untagged actions as safe to run directly.
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