Security audit
Security checks for vulnerabilities and agentic risk
The DeepL workflow fits its purpose, but setup executes unverified remote code and leaves broader changes to agent skills uncontrolled.
Review and install a verified CLI release yourself before use, and check or disable automatic synchronization of other agent skills. Translation text passes through OOMOL to DeepL and may consume paid quota. The bundled instructions were fully inspected, but the remote installer and server-side credential handling remain unverified; no malicious intent was established.
The only visible operation is remote installer execution, rather than the declared DeepL functionality. Dependency installation can be a supporting implementation detail, but the supplied chunk does not establish that this installer supports DeepL. The downloaded script is not provided, so its further behavior cannot be determined.
The supplied chunk only invokes a login command; it does not search or read DeepL data or visibly identify DeepL as the authentication target. Authentication could support an integration, but the supplied code does not establish that connection and contains none of the declared functionality.
The fallback pipes a remotely fetched, unpinned installer directly into Bash without integrity verification or review; the PowerShell alternative uses the same download-and-execute pattern. If the distribution endpoint or delivery chain is compromised, attacker-controlled code could execute with the agent's local privileges and access available files or credentials; limiting installation to a missing-CLI error reduces exposure but does not eliminate it.
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 workflow instructs the agent to execute connector actions and declares all untagged actions safe to run directly, including translate_text. Although the skill identifies OOMOL and DeepL, it does not warn that translation payloads leave the user's environment and may contain sensitive or confidential information.
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