Security audit
Security checks for vulnerabilities and agentic risk
The TabAPI functions fit the stated purpose, but automatic setup executes remote installers without clearly limiting their effects or requiring your approval.
Review and approve CLI installation separately before allowing this skill to run its setup fallback, including any changes to other agents' skills. OOMOL mediates account access and requests; consider what you submit and applicable usage charges. The sole bundled artifact was fully inspected, but external installer behavior remains unverified. No malicious intent or credential theft was established.
The supplied command performs remote script execution, not TabAPI searching or reading. Nothing in the supplied content establishes the Oomol installer as a supporting dependency for TabAPI. The downloaded script is not provided, so its additional behavior cannot be determined.
The supplied chunk performs only a CLI login, with no demonstrated connection to TabAPI. Authentication could be a supporting implementation detail if that connection were established, but the provided content does not establish it or implement the declared functionality. No credential theft or other malicious behavior can be inferred from this command alone.
Piping an HTTPS response directly into Bash executes mutable remote code without version pinning, independent integrity verification, or prior review. HTTPS protects transport but not against a compromised publishing endpoint; successful exploitation could compromise files, credentials, and other resources accessible to the agent's execution account.
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 execute remotely supplied shell or PowerShell code without explaining its permissions or obtaining approval for local system changes. Although limited to missing-CLI errors, this can turn a data-reading request into arbitrary code execution with the agent process's privileges if the installer source is compromised.
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