Security audit
Security checks for vulnerabilities and agentic risk
The Altiria actions have clear approval safeguards, but setup can execute unverified remote installers and introduce broader agent changes without separate user approval.
Review and approve CLI installation separately, verify the installer or release, and decide whether automatic installation of other agent skills is acceptable. This integration relies on OOMOL for connected-account access and processing requested data. Confirm SMS recipients, message content, and contact changes before execution. No malicious payload was established; external installers and hosted runtime behavior remain unverified.
The supplied code installs a third-party CLI through remote shell execution; it does not show any Altiria data operations or establish that the installer supports them. The downloaded script's contents and subsequent effects cannot be determined from this chunk.
Piping the HTTPS installer directly into bash executes remote content without a pinned version, integrity check, or opportunity to inspect the complete script first. HTTPS protects transport but does not protect against a compromised distribution endpoint; malicious installer content could execute with the user's permissions. This is the same underlying installation risk highlighted by SQP-2, not evidence of a separate malicious payload.
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 instructs the agent to execute downloaded shell or PowerShell code without first obtaining approval for local software installation. Although triggered only when the CLI is missing, this expands an Altiria task into arbitrary code execution with the invoking user's permissions and could expose local files or credentials if the installer is compromised.
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