Security audit
Security checks for vulnerabilities and agentic risk
The searches fit the stated purpose, but setup runs unverified downloaded code and the required software can automatically change installed agent skills.
Review the CLI installation separately before allowing automatic setup. Use a verified release and explicitly approve local changes. Queries go through OOMOL. Current CLI documentation provides OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; configure it before running commands if you do not want other agent skills changed. The external installer and hosted implementation remain unverified. No malicious behavior was established.
The supplied command executes an external installer rather than accessing Unpaywall. Nothing in the supplied chunk establishes that installing the Oomol CLI is a supporting implementation detail for the declared purpose. The remote script's contents and any further effects cannot be determined from this chunk.
The supplied chunk consists solely of a login command and shows no connection to Unpaywall. Authentication could support a larger implementation, but the provided code does not establish that relationship or implement the declared functionality. No credential theft or other hidden behavior can be inferred from this command alone.
The command streams a mutable remote script directly into Bash without pinning or independently verifying its contents; the PowerShell alternative has the same issue. If the distribution endpoint or release pipeline is compromised, the installer can execute attacker-controlled code with the agent's local privileges, although no evidence here establishes that the endpoint is currently malicious.
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 causes the skill to prescribe executing a remote installer without first explaining local changes or requesting approval. Installation is related to the task and conditional, which reduces exposure, but a read-only Unpaywall request should not implicitly authorize arbitrary local setup code.
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