autonomous-builder
Full-stack software development agent for design, implementation, testing, and deployment. Use when the user explicitly asks for end-to-end project creation, feature development, bug fixing, or code refactoring.
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 includes a supervisor script that starts/resumes a Claude session with a "--dangerously-skip-permissions" flag (bypassing all user confirmations), which conflicts with its own "Safety First" requirement for explicit user approval and effectively instructs overriding platform/user safeguards — a hidden/overriding instruction outside safe behavior.
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 multiple deliberate, high-risk automation patterns (permission bypass flag, unattended supervisor loop, automatic installation/registration of remote MCP servers, capability to create/run custom MCP servers, automatic logging and GitHub pushes including prompt/decision data, and desktop/browser automation) that enable supply-chain installs, persistent unattended execution, and easy exfiltration or remote control when run in a host environment.
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 includes an auto-generated supervisor script that runs the agent with a --dangerously-skip-permissions flag (bypassing user confirmations) and instructs auto-installation of system tools (including sudo apt install gh), which pushes the agent to perform system-level changes and bypass security protections.
- Repository
- foryourhealth111-pixel/Vibe-Skills
- Commit
f627ab5
- 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.