Ae4
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a broad automation skill that is mostly transparent, but it asks agents to run commands, move files, make network requests, schedule/watch workflows, and publish content without clear safety limits.
Review this skill before installing. Use it only when you intentionally want broad workflow automation, and require explicit approval before it runs shell commands, posts content, uploads data, watches folders, schedules recurring jobs, or reads/writes files outside a chosen project directory.
Suspicious Unicode normalization or mixed-script content
The trigger keywords include very broad terms such as 'builder', 'automation', and 'workflow', which can cause the skill to activate for ordinary user requests unrelated to this specific skill. Because the skill advertises read and exec capabilities, over-broad invocation increases the chance that powerful file or command actions are suggested or used in the wrong context.
The skill explicitly promotes file operations, network requests, and command execution but does not provide user-facing guardrails about consent, path restrictions, secret handling, or confirmation before destructive or external actions. In an agent environment, these capabilities materially increase the risk of unauthorized file access, data exfiltration, or dangerous shell execution if the skill is triggered on ambiguous requests.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
const workflow = {
trigger: { type: "cron", schedule: "0 */6 * * *" },
steps: [
{ action: "fetch", url: "https://api.example.com/data" },
{ action: "transform", script: "process(data)" },
{ action: "save", path: "./output/data.json" }
]