Security audit
Security checks for vulnerabilities and agentic risk
The Tuskr workflow includes approval safeguards, but its setup instructions can trigger unverified remote code installation without separate user approval.
Review the CLI installation separately before enabling this skill, and require approval before any downloaded installer runs. The fallback executes third-party code, and publisher documentation describes additional agent-skill installation. Connecting Tuskr gives OOMOL access to the authorized account data; retain the skill's exact-payload confirmation requirement for changes. The bundled file shows no evidence of malicious intent, but external installer behavior remains outside this artifact review.
The supplied command executes an external installer and shows no Tuskr data operations or evidence that this installation supports them. This is materially different from the declared Tuskr purpose. The downloaded script's contents are not supplied, so its additional effects cannot be determined.
Piping the HTTPS response directly to bash executes mutable remote content without reviewing it or verifying a pinned artifact. HTTPS protects transport but does not protect against compromise of the installer host or publishing process, which could yield arbitrary code execution with the invoking user's access; this is the same underlying installation risk identified by SQP-2.
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 fallback directs installation by executing downloaded shell or PowerShell scripts without requiring informed user approval or integrity verification. Although limited to a missing dependency, this can turn an ordinary Tuskr request into local code execution with the agent's privileges if the installer source is compromised; the declared oo-only tool allowance may limit reachability but does not make the instructions safe.
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