Security audit
Security checks for vulnerabilities and agentic risk
The DataCite functions fit the description, but setup can execute unverified downloaded code without a separate approval step.
Review and verify a pinned CLI installation before enabling this skill, and require approval for setup changes. Review or disable the CLI's automatic bundled-skill synchronization. Use a DataCite key limited to the records you intend to access through OOMOL. The remote installer contents and server-side credential protections were not verified; no malicious behavior was established.
The supplied command performs remote software installation rather than searching or reading DataCite data. Although installation can be a supporting implementation detail, the supplied chunk establishes no connection between this installer and the declared DataCite functionality. The downloaded script's contents are not supplied, so its further behavior cannot be determined.
The supplied code performs authentication rather than DataCite searching or reading. Nothing in the chunk establishes that oo is a DataCite client or that this login is a supporting step for the declared functionality.
Piping the HTTPS installer directly into Bash executes mutable remote content without inspecting it or checking a pinned version, signature, or independently trusted digest. HTTPS protects transport but does not prevent malicious changes at the distribution source, so a compromised installer could execute arbitrary code with the invoking process's privileges; this is the same underlying installation risk identified by SQP-2.
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 directs the agent to execute downloaded shell or PowerShell code without explicit user approval, integrity verification, or a warning about local system changes. Although conditional on a missing CLI, this turns a read-only DataCite request into execution of remote code with the agent process's privileges, potentially exposing local files and credentials if the distribution channel 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