Security Audit

pskoett/pskoett-ai-skills:skills/simplify-and-harden

github.com/pskoett/pskoett-ai-skills

AI SkillCommit 3b2f47ccd231

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

pskoett/pskoett-ai-skills:skills/simplify-and-harden received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill modifies agent's system prompt/configuration files.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on March 3, 2026 (commit 3b2f47cc). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill modifies agent's system prompt/configuration files The skill, through its 'Self-Improvement Integration (Learning Loop)', is designed to promote 'promotion-ready patterns' into agent context/system prompt files (e.g., `CLAUDE.md`, `AGENTS.md`, `.github/copilot-instructions.md`, or equivalent). This grants the skill the ability to directly modify the agent's core instructions and configuration. If the skill's logic for generating these patterns is flawed, or if the skill itself were compromised, it could lead to prompt injection into the agent's system prompts, potentially altering its behavior, security posture, or leading to data exfiltration. This represents a significant privilege that could be misused. 1. Implement robust validation and sanitization for all generated 'suggested_rule' content before it is written to agent context files, ensuring no malicious instructions or sensitive data can be injected. 2. For critical agent context files, consider adding a mandatory human review step before any automated promotion of rules. 3. Re-evaluate if direct modification of agent system prompt files is strictly necessary; consider alternative mechanisms like generating suggestions for human review or updating less privileged configuration files. 4. Implement a mechanism to easily revert changes made to agent context files.	LLM	SKILL.md:296

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/eed9eb61e33d0bb2.svg)](https://skillshield.io/report/eed9eb61e33d0bb2)