Security audit
Security checks for vulnerabilities and agentic risk
The Qlty features fit the stated purpose, but setup directs the agent to run unverified online installers without a clear user approval step.
Review the installation fallback before enabling this skill. Prefer installing a verified CLI release yourself and require approval before the agent installs software. Connecting Qlty authorizes OOMOL to mediate account access. The main concern is uncontrolled setup execution; the artifacts do not show malicious intent or unrelated data collection.
The supplied command targets Oomol rather than Qlty and executes a remote installer. This is materially different from the declared Qlty data-access purpose, with no visible connection establishing it as a supporting implementation detail. The downloaded script is not supplied, so its additional effects cannot be determined.
Authentication can be a supporting implementation detail, but the supplied chunk contains only a login command for oo, with no demonstrated connection to Qlty. As supplied, its behavior does not substantiate the declared Qlty search-and-read purpose.
The command pipes a live HTTPS response directly into Bash without pinning or verifying the installer contents. Compromise of the installer hosting or distribution pipeline could therefore execute attacker-controlled code with the invoking user's privileges, potentially exposing local files and credentials; HTTPS alone does not protect against a compromised publisher.
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 of executable software without first obtaining approval for local system changes or explaining that remotely supplied code will run. The missing-command condition limits exposure, but a request to read Qlty data does not itself authorize installing software; an agent following the fallback could make unexpected host changes.
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