Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation helper that reads project files to write or audit README files, with no executable code, persistence, or hidden data handling found.
Install this if you want README files written or reviewed using the Standard Readme format. Be aware that it may activate for broad README requests and will inspect normal repository files to infer accurate install, usage, license, and contribution details.
The invocation guidance is broad enough to auto-select this skill for many generic README requests, even when the user did not ask for Standard Readme-specific behavior. Over-broad routing can cause the wrong skill to access repository files and steer outputs toward a specific format, creating unintended data exposure and misapplication risk in agentic environments.
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.
When creating or rewriting a README:
1. **Gather context** - Read the project's existing files to understand what it is: package.json/Cargo.toml/pyproject.toml (name, description, dependencies), existing README, LICENSE, CONTRIBUTING.md, source code structure, CI config. Don't ask the user for information you can derive from the codebase.
2. **Determine relevant sections** - Start with the required sections. Add optional sections only when the project justifies them:
- Banner: only if an image already exists in the repo
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.
"Object" form shall mean any form resulting from mechanical transformation or
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.
"Object" form shall mean any form resulting from mechanical transformation or
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.
"Object" form shall mean any form resulting from mechanical transformation or
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.
"Object" form shall mean any form resulting from mechanical transformation or
No suspicious patterns detected.