Security audit
Security checks for vulnerabilities and agentic risk
The search functions fit the stated purpose, but setup can execute unverified software and introduce persistent agent changes without clear user control.
Review and install the CLI separately before enabling automatic use. Verify the release and review or disable its automatic skill synchronization. Search inputs pass through OOMOL and AnySearch, and usage may incur charges. The bundled instructions were fully inspected; the remote installers and resulting binaries were not verified.
The supplied code contains no AnySearch interaction. Instead, it executes an external installation script from cli.oomol.com, with no demonstrated connection to the declared AnySearch functionality. This is a material behavioral mismatch, not an established supporting implementation detail. The remote script's contents and resulting system changes are not available for assessment.
The supplied chunk performs only a login operation and contains no AnySearch search, reading, or identifiable integration. Authentication could be a supporting implementation detail if connected to AnySearch, but no such connection is established in the supplied code; as presented, its primary behavior differs from the declared purpose.
Piping a mutable remote installer directly into Bash executes its contents without independent integrity verification or an opportunity for review. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's permissions; HTTPS and the legitimate setup context do not eliminate this 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 missing-CLI recovery path directs the agent to execute remotely downloaded shell or PowerShell code without explaining the system changes or requiring explicit installation approval. Although conditional and plausibly legitimate, this turns a search task into host-level code execution with the invoking user's permissions; it overlaps with SC2 rather than representing an independent exploit.
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