Security audit
Security checks for vulnerabilities and agentic risk
The search workflow fits its purpose, but first-time setup directs the agent to execute an unverified remote installer without a separate approval step.
Review setup before enabling this skill. Install a verified CLI release yourself and require approval before any downloaded installer runs. Confirm whether the CLI will install or update skills in other agent applications. OOMOL is a disclosed intermediary for your Hybrid Analysis connection. The review concern is setup control and scope; the bundled search instructions show no evidence of malicious intent.
The visible behavior is remote installer execution, not the declared Hybrid Analysis data access. Installation could be a supporting implementation detail if its relationship to the skill were established, but the supplied chunk provides no such connection. The downloaded script's contents and downstream effects are unknown; this finding does not imply that the installer is malicious.
The supplied chunk contains only a login command and shows no Hybrid Analysis interaction. Authentication could support a declared service integration, but nothing in this chunk connects oo auth login to Hybrid Analysis. Its visible primary behavior therefore differs materially from the declared purpose.
Piping an HTTPS response directly into bash executes mutable remote content without an integrity check or review opportunity. HTTPS protects transport but not against a compromised publishing endpoint, and the conditional setup context reduces exposure without eliminating the possibility of local code execution and credential theft.
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 setup instructs execution of remotely fetched shell and PowerShell scripts without inspecting or independently verifying their contents, or requiring approval for installing software. Although conditional and relevant to the CLI dependency, this can execute attacker-controlled code with the invoking user's privileges if the distribution endpoint or release pipeline is compromised; it overlaps with SC2.
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