Security audit
Security checks for vulnerabilities and agentic risk
The Coda workflow has sensible controls, but its setup instructions can trigger unverified remote code execution without a separate approval step.
Review the CLI installation before allowing this skill to perform setup. Install a verified, version-specific release separately and require approval for additional local changes. Connecting Coda entrusts OOMOL with the integration credentials and requested data. Keep the skill's confirmation requirements for Coda writes. The installer payloads were unavailable for inspection; no malicious behavior was established.
The supplied chunk performs remote installer execution rather than Coda data operations. Although installing tooling can be a supporting implementation detail, the supplied content does not establish that this installer supports Coda. The remote script's contents and any resulting system changes are not visible, so no more specific behavior can be confirmed.
Piping a mutable HTTPS installer directly into bash executes the remote response with the agent process's local privileges, without integrity verification or an opportunity to inspect it. Compromise of the distribution endpoint could expose local files and credentials or modify the system; the legitimate vendor domain and missing-CLI prerequisite reduce suspicion of malicious intent but do not remove the 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 fallback directs the agent to install software by immediately executing downloaded scripts, without requiring explicit approval for local system changes or reviewing the installer. Although setup is relevant and only triggered when the CLI is missing, an ordinary Coda request can thereby lead to local code execution outside the requested data operation.
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