Security audit
Security checks for vulnerabilities and agentic risk
The literature tools match the stated purpose, but setup can execute unverified downloaded software without clear user approval.
Review setup before installing. Prefer a reviewed, version-pinned CLI installation and require approval for software installation or changes to other agent skills. Searches pass through OOMOL. The external installers were unavailable for inspection, so their exact effects remain uncertain; no malicious intent was established.
The fallback expands a read-only literature task into downloading and executing an installer on the agent's host without explicit approval or integrity verification. Installing the documented connector CLI is a plausible prerequisite rather than evidence of malicious intent, but a compromised installer could execute arbitrary code with the agent's permissions.
The supplied code only invokes a login command; it does not search or read Europe PMC data or identify Europe PMC as its target. Authentication could support a service integration, but the provided chunk establishes no such connection, so its observable purpose differs materially from the declared purpose.
Piping an HTTPS response directly into bash executes mutable remote content without a pinned version, signature verification, or prior inspection; the PowerShell alternative has the same issue. HTTPS protects transport but does not protect against a compromised distribution endpoint or malicious installer release, which could gain the agent's local privileges.
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 missing-command fallback instructs installation without obtaining approval for local system changes or explaining that downloaded code will run. Although conditional and related to setup, it crosses the boundary from reading publications to executing software, potentially exposing files and credentials accessible to the agent.
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