Security audit
Security checks for vulnerabilities and agentic risk
The CMS workflow fits its purpose, but setup can execute unverified installers and introduce broader agent changes without clear user control.
Review setup before enabling this skill. Install a verified CLI release yourself, approve any agent-skill changes, and consider disabling managed-skill synchronization using the documented OO_SKILLS_SYNC_DISABLED setting. OOMOL mediates CMS access, so connect only the intended account with read-only permissions where available. The remote installers and hosted implementation were not verified; the supplied artifacts do not establish malicious behavior.
The supplied command runs an Oomol installer, with no visible Agility CMS interaction. Installing and executing remote software is not declared, and the supplied code establishes no connection showing that this is a supporting implementation detail for Agility CMS access. The remote script's exact effects cannot be determined from this chunk.
The only supplied behavior is a login command, rather than the declared Agility CMS data-access functionality. Authentication could be a supporting implementation detail, but this chunk provides no evidence that the command authenticates to Agility CMS or supports the described operations.
The command pipes a mutable remote script directly into Bash without pinning or verifying the downloaded code. HTTPS protects transport but does not protect against a compromised distribution endpoint or malicious release, which could result in arbitrary execution under the user's account; the legitimate setup context reduces suspicion of malicious intent, not the technical 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 fallback setup directs the agent to execute downloaded shell or PowerShell code without explicit approval or disclosure of the resulting system changes. Although conditional and relevant to setup, this crosses from reading CMS data into arbitrary local code execution; a compromised installer could access files and credentials or establish persistence with the invoking user's permissions.
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