Security audit
Security checks for vulnerabilities and agentic risk
The image workflow makes sense, but its setup runs unverified remote code and omits documented changes to other agents’ installed skills.
Review and preinstall a verified CLI version before enabling this skill. Check and control its documented startup skill synchronization, which can affect other agent installations. Send only HTML/CSS you intend OOMOL and the rendering provider to process. Remote installer contents were unavailable, so their exact behavior remains uncertain.
The supplied chunk contains only a login command, with no HTML processing, image generation, or related data retrieval. Authentication could be a supporting implementation detail if its connection to html2img.com were established, but the supplied content provides no such connection and does not implement the declared purpose.
The supplied chunk performs remote installer execution rather than an HTML-to-image operation. Installation could be a supporting implementation detail, but the provided content does not establish that this installer supports html2img.com or the declared workflow. The remote script's contents and downstream effects are not available for assessment.
The fallback pipes a remotely fetched, unpinned script directly into Bash without integrity verification or review; the PowerShell alternative has the same execution pattern. If the distribution endpoint or publishing pipeline is compromised, attacker-controlled code runs with the agent process's permissions, potentially exposing local files and credentials; restricting this to missing-CLI recovery reduces frequency but not impact.
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
Raw HTML and CSS may contain confidential content, embedded tokens, or personal data, and this workflow sends the payload through OOMOL to an external rendering service without a sensitive-data check. The external-service purpose is disclosed, which reduces surprise, but the broad instruction to use this skill for any HTML-to-image request can still cause unintended disclosure of private input.
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