computer-use-agents
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives.
62
55%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/computer-use-agents/SKILL.mdSecurity
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 1.00). The skill requires the LLM to emit actionable JSON (e.g., {"type":"type","text":"..."}) and bash/tool commands that may include user credentials or tokens verbatim (for logins, typing, or API calls), which forces secrets to appear in model outputs and creates an exfiltration risk.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill's BrowserUseAgent explicitly captures page snapshots (get_page_snapshot) and feeds page DOM/text/URL into the LLM in run_with_llm (with examples like "Go to weather.com"), and the vision-based agents also pass screenshots to the model, so arbitrary public webpages and user-generated web content are fetched and interpreted to drive actions—creating a clear vector for indirect prompt injection.
- Repository
- sickn33/antigravity-awesome-skills
- Commit
93c57b2
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.