Security audit
Security checks for vulnerabilities and agentic risk
The Readwise workflow is coherent, but setup can execute an unchecked downloaded installer and introduce broader changes to agent skills without clear user control.
Review the CLI installation separately before allowing automatic setup. Check which agent skills it installs or updates and consider disabling startup synchronization using the publisher's documented OO_SKILLS_SYNC_DISABLED setting ([command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)). Connecting Readwise authorizes OOMOL to access that account; confirm each proposed data change. The review concern is setup control and under-disclosed persistent changes, not evidence of data theft or malicious intent.
The supplied chunk installs software from cli.oomol.com rather than performing Readwise operations. Although installation can be a supporting implementation detail, nothing supplied establishes that this installer supports Readwise. The downloaded script's contents and subsequent effects are not visible, so no additional behavior can be confirmed.
The curl-to-bash pipeline immediately executes the remote response without version pinning or independent integrity verification. If the installer distribution infrastructure is compromised, an attacker could execute code with the agent's permissions and potentially access local files or credentials; the legitimate OOMOL dependency and HTTPS transport do not eliminate that supply-chain risk.
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 setup instructions direct the agent to execute downloaded shell or PowerShell code when the CLI is missing, without requiring explicit approval for local software installation or explaining its effects. This fallback is conditional, which limits exposure, but it can turn an ordinary Readwise request into execution of unreviewed code with the agent's local permissions.
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