Security audit
Security checks for vulnerabilities and agentic risk
This is a security-review guidance skill with disclosed, purpose-aligned behavior and no embedded execution or hidden data movement.
Install this if you want an assistant to apply security-review checks during security-sensitive coding or audits. Prefer explicit prompts when invoking it, and confirm where audit reports should be written so generated Markdown files do not surprise you in a repository.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Workspace-local (recommended for a single project/agent):
mkdir -p ./skills
cp -R ./unified-security ./skills/
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Project-local:
mkdir -p .claude/skills
cp -R ./unified-security .claude/skills/
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Global:
mkdir -p ~/.claude/skills
cp -R ./unified-security ~/.claude/skills/
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Project-local:
mkdir -p .codex/skills
cp -R ./unified-security .codex/skills/
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Global:
mkdir -p ~/.codex/skills
cp -R ./unified-security ~/.codex/skills/
The top-level description is broad enough to activate the skill across many common coding tasks involving auth, input, databases, deployment, dependencies, or AI workflows. Overbroad triggering can cause an agent to apply this skill in contexts the user did not intend, increasing the chance of unnecessary invasive analysis or follow-on actions such as file modification recommendations.
The "Use When" section enumerates many broad scenarios without constraints, negative examples, or a requirement for user opt-in. In an autonomous agent ecosystem, this can make the skill trigger too aggressively and expand the agent's scope into security auditing behavior that may not match the task, increasing the risk of over-collection, noisy findings, or unintended workflow changes.
The skill explicitly instructs the agent to save an audit report into the project folder, which adds file-write behavior beyond pure analysis guidance. In an agent setting, even benign autonomous writes can create unwanted workspace modifications, overwrite user files, or normalize side effects without explicit user approval.
The instruction to save a markdown report into the project folder lacks any warning that this will modify the workspace or any requirement to confirm with the user first. In agent environments, silent writes are risky because they can surprise users, pollute repositories, or create compliance issues when generated artifacts are added without review.
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.
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
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.
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
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.
exercising 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
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.
exercising 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
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.
exercising 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
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.
exercising 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
No suspicious patterns detected.