Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent AI-writing review skill, with expected repository scanning and report writing but no evidence of hidden, destructive, or exfiltrating behavior.
Install this if you want repository text reviewed for AI-like writing patterns. Be aware it can read developer docs, comments, docstrings, commit messages, and on PR branches the PR body via gh; it also writes a .beagle report file. Use a specific path or category when you do not want a broad scan, and avoid --all unless scanning the whole codebase is intended.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
<!-- Before -->
It's worth noting that the connection pool defaults to 10.
<!-- After -->
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Bolding common terms throughout a paragraph:
<!-- BAD - Every term is bold, nothing stands out -->
The **server** reads the **configuration file** on **startup** and
initializes the **database connection pool**. If the **connection**
fails, the **retry logic** kicks in with **exponential backoff**.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
delve, utilize, leverage (meaning "use"), whilst, furthermore, moreover, harnessing, revolutionize, paradigm, synergy, facilitate, empower, elevate, unleash, robust (non-technical), seamless, cutting-edge, endeavor, pivotal, embark
<!-- BAD -->
Let's delve into how this module leverages the cache to facilitate
seamless data retrieval, empowering developers to unleash the full
potential of the framework.
The manifest description is broad enough to match many ordinary review requests, including generic writing-quality tasks. Overbroad invocation criteria increase the chance the skill is auto-selected in contexts outside narrow AI-writing detection, causing unnecessary repository scanning, git inspection, and report-writing behaviors.
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.
### 2. Load Skills
Load the [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) skill before reporting findings. The AI-writing pattern catalog lives in this file's Reference Material section and the `references/*.md` files — read the categories you intend to check.
### 3. Determine Scope
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.
### 2. Load Skills
Load the [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) skill before reporting findings. The AI-writing pattern catalog lives in this file's Reference Material section and the `references/*.md` files — read the categories you intend to check.
### 3. Determine Scope
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.
### 2. Load Skills
Load the [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) skill before reporting findings. The AI-writing pattern catalog lives in this file's Reference Material section and the `references/*.md` files — read the categories you intend to check.
### 3. Determine Scope
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.
### 2. Load Skills
Load the [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) skill before reporting findings. The AI-writing pattern catalog lives in this file's Reference Material section and the `references/*.md` files — read the categories you intend to check.
### 3. Determine Scope
The instruction to run gh pr view --json body gives the skill external-service access beyond local text review. This can pull remote repository metadata or private PR content without explicit user awareness, which is risky in restricted or privacy-sensitive environments.
The skill tells the agent to read PR descriptions from GitHub without any user-facing disclosure that external metadata may be accessed. In environments with private repos or compliance controls, silent network-backed retrieval can expose sensitive content and violate user expectations.
The skill is described as a review tool for developer text, but it also instructs the agent to create a directory and write a JSON file into the repository. That expands it from read-only analysis into state-changing behavior, which can surprise users, alter working trees, and be abused in automation contexts where review skills are expected not to modify project contents.
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.
Detecting AI-generated writing in developer documentation: docstrings, code comments, commit messages, and PR descriptions.
> **Overlap note:** Tautological docstrings and obvious comments also appear in [llm-artifacts-detection](../../../../beagle-core/skills/llm-artifacts-detection/SKILL.md) (style-criteria.md). This file focuses on the AI writing style aspect; the artifacts skill focuses on unnecessary code artifacts.
---
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.
Detecting AI-generated writing in developer documentation: docstrings, code comments, commit messages, and PR descriptions.
> **Overlap note:** Tautological docstrings and obvious comments also appear in [llm-artifacts-detection](../../../../beagle-core/skills/llm-artifacts-detection/SKILL.md) (style-criteria.md). This file focuses on the AI writing style aspect; the artifacts skill focuses on unnecessary code artifacts.
---