Security audit
Security checks for vulnerabilities and agentic risk
The Datagma integration is coherent, but automatic setup runs unverified downloaded code and can install additional agent instructions without clearly disclosing that effect.
Review and verify the CLI installation separately before allowing automatic setup. Consider disabling cross-agent skill synchronization; the publisher documents OO_SKILLS_SYNC_DISABLED for this purpose. Submit only lookup details you intend to share with OOMOL and Datagma, and consider account credit usage. The remote installers were unavailable for inspection, so their exact behavior remains uncertain; no malicious behavior was established.
The supplied command performs remote script execution from an Oomol installation endpoint rather than searching or reading Datagma data. Nothing in the supplied content establishes this installer as a supporting dependency for Datagma access. The downloaded script's contents and further effects are not available for inspection.
The setup instructions pipe a mutable remote script directly into Bash without inspecting it or verifying an independently trusted signature or digest; the PowerShell alternative has the same weakness. If the distribution endpoint or release infrastructure is compromised, the script can execute attacker-controlled code with the agent process's permissions, potentially accessing local files and credentials. Conditional execution only when the CLI is missing reduces exposure but does not remove this supply-chain risk.
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 JSON payloads, which for the listed enrichment and contact-search actions can contain names, email addresses, and profile URLs sent through OOMOL to Datagma. Although the connector is identified, no privacy warning explains this sharing, and the safety section instead treats all untagged reads 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