boltz-protein-design
Design new protein binders with Boltz. Use when generating protein, peptide, antibody, nanobody, or custom binder candidates for a target. Not for screening existing proteins or small molecules.
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
3 findings: 2 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill explicitly tells the agent to perform authentication without asking the user and to request sandbox bypass/escalation for installs/auth (instructions to evade consent or host sandbox), which are deceptive and outside a purely design-guidance purpose.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The skill contains explicit instructions to bypass agent sandboxing and to perform authentication flows "without asking permission first", which enable unauthorized network access and credential/privilege escalation and therefore present a high-risk, intentional abuse vector.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly directs the agent to request sandbox bypass/escalation for user-wide CLI install, browser login, credential storage, temp files, or API access and to run auth actions without asking permission, which pushes the agent to bypass security mechanisms and change host state.
- Repository
- openai/plugins
- Commit
11c74d6
- 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.