Security audit
Security checks for vulnerabilities and agentic risk
The BambooHR reads fit the stated purpose, but setup can execute unchecked downloads and introduce broader agent changes without clear user control.
Review and verify the CLI installation separately before allowing setup. Decide whether its additional managed skills are wanted; upstream documents OO_SKILLS_SYNC_DISABLED=1 to suppress startup synchronization. Connect only an appropriately restricted BambooHR account and consider OOMOL's role in handling employee data. The bundled instructions were fully inspected, but remote installer contents and the exact version they would install remain unverified.
The supplied code installs software from an external CLI distribution endpoint rather than performing the declared BambooHR operations. Nothing in the provided chunk establishes that this installation is a supporting dependency for BambooHR access. The downloaded script's contents are unavailable, so its further behavior cannot be determined.
Piping the HTTPS response directly into bash gives the downloaded script immediate execution without an integrity-verification step. Compromise of the installer host or release pipeline could expose local files, available credentials, and the agent environment. The vendor-related domain and missing-CLI prerequisite make this a plausible setup procedure, not evidence of malicious intent, but do not establish script integrity.
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
Both setup commands execute downloaded scripts without first verifying a pinned version, signature, or trusted digest. A compromised distribution endpoint could therefore execute arbitrary code with the agent process's permissions; the conditional setup trigger reduces exposure but does not remove the risk. The substantive issue is unverified execution, not merely the absence of a warning.
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