Security audit
Security checks for vulnerabilities and agentic risk
The Sendbird workflow has clear approval controls, but its fallback setup runs an unverified remote installer without a separate approval step.
Review and approve CLI installation separately before allowing the missing-command fallback. Check its settings for installing or synchronizing other agent skills, use narrowly scoped Sendbird access, and retain the documented confirmations for changes and deletions. OOMOL mediates the connection; its remote installer and hosted connector were not audited here. No artifact-backed malicious behavior was found.
The supplied code installs software from an Oomol domain rather than performing Sendbird operations. No visible code establishes that this installer is a supporting dependency for the declared purpose. The remote script's contents and subsequent behavior cannot be determined from this chunk.
The command executes a remotely fetched, mutable script directly in a local shell without version pinning or independent integrity verification; the PowerShell alternative uses the same fetch-and-execute pattern. If the distribution endpoint or delivery pipeline is compromised, attacker-controlled code could run with the invoking user's permissions, although the vendor-related URL and missing-CLI prerequisite make this a supply-chain exposure rather than evidence of intentional exfiltration.
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 missing-command fallback directs the agent to install software without explicitly obtaining approval for local system changes. Installation is relevant to the task and conditional, which reduces concern about malicious intent, but permission to operate Sendbird does not necessarily authorize modifying the host; the declared oo-only tool restriction may also prevent these commands in a strictly enforced environment.
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