Security audit
Security checks for vulnerabilities and agentic risk
The searches match the stated purpose, but setup executes unverified downloaded code and leaves broader changes to other agent skills unexplained.
Review and install the CLI separately before allowing automated use. Its documented OO_SKILLS_SYNC_DISABLED setting can prevent startup deployment of other agent skills; see the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the intended TheirStack account and consider that queries pass through OOMOL. The remote installers and hosted credential handling were not verified; no malicious behavior was established.
The supplied command installs software from an Oomol domain rather than searching or reading TheirStack data. No connection to TheirStack or need for this installer is established, so this is an undeclared capability and inconsistent resource access, not an evidenced supporting implementation detail. The downloaded script's further behavior cannot be determined from the supplied chunk.
The command pipes a live network response directly into Bash without pinning or independently verifying the script; the PowerShell alternative uses the same fetch-and-execute pattern. If the distribution endpoint or delivery pipeline is compromised, an attacker could execute code with the invoking user's privileges, potentially accessing local credentials or modifying files; HTTPS alone does not establish script integrity.
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
A missing CLI triggers instructions to execute a remote installer without explicitly obtaining approval for local software installation and arbitrary code execution. Although conditional on a setup failure, this expands a data-reading request into potentially persistent system changes under the executing user's privileges; the declared Bash allowlist may restrict execution but is not an installation-consent safeguard.
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