Security audit
Security checks for vulnerabilities and agentic risk
Review is warranted because a missing prerequisite triggers execution of downloaded software without verification or a separate approval step.
Review and approve CLI installation separately, using a verified release and checking whether it installs additional agent skills. Send only intended content through OOMOL/APIpie AI and confirm acceptable generation costs. The bundled instructions were fully reviewed, but remote installers and live connector implementations were not verified; no artifact-backed malicious behavior was found.
The supplied chunk performs remote installer execution rather than APIpie AI data operations. Nothing in the chunk establishes that this installation supports the declared purpose. The downloaded script's contents are not supplied, so its downstream behavior cannot be determined.
Piping a mutable HTTPS download directly into bash executes remote code without first verifying the artifact's integrity or provenance. HTTPS protects transport but not against a compromised vendor endpoint or malicious installer update, either of which could compromise files and credentials accessible to the process; this overlaps with the fallback-installation finding.
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 workflow instructs the agent to submit action payloads through the connector, including chat or embedding inputs when those actions are selected. Although the service integration is identified, the skill does not warn that submitted content leaves the user's environment and is processed by third-party services; the state-change confirmations do not address this privacy impact.
The untagged create_chat_completion action inherits the instruction that untagged actions are reads and safe to run directly, despite performing model inference that can consume paid credits and transmit prompt content. This creates a misleading authorization shortcut, although the requirement for an APIpie-related user task limits the scope and does not establish that persistent data is modified.
The fallback directs the agent to execute downloaded shell or PowerShell scripts without an explicit installation approval or artifact-verification step. A compromised distribution endpoint could therefore run arbitrary code with the invoking user's privileges; restricting installation to a missing-CLI error reduces frequency but does not prevent compromise.
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