Security Audit

abnormal-self-generate

github.com/pbuff07/skill-test

AI SkillCommit 3d94533d6ab2

CRITICAL

Scanned 20 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

abnormal-self-generate received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 6 findings: 2 critical, 3 high, 1 medium, and 0 low severity. Key findings include Covert behavior / concealment directives, Persistence / self-modification instructions, File read + network send exfiltration.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 25/100, indicating areas for improvement.

Last analyzed on July 1, 2026 (commit 3d94533d). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

25%

Static Code Analysis

63%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

3 findings

Shell Execution

2 findings

Excessive Permissions

3 findings

Security Findings6

Severity	Finding	Layer	Location
CRITICAL	Persistence / self-modification instructions Crontab manipulation (list/remove/edit) Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles.	Manifest	abnormal-self-generate/SKILL.md:4
CRITICAL	File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	abnormal-self-generate/SKILL.md:4
HIGH	Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	abnormal-self-generate/SKILL.md:4
HIGH	Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_rsa'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	abnormal-self-generate/SKILL.md:4
HIGH	Sensitive path access: AWS credentials Access to AWS credentials path detected: '~/.aws/credentials'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	abnormal-self-generate/SKILL.md:4
MEDIUM	Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter.	Static	abnormal-self-generate/SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a9765a21685db2a8.svg)](https://skillshield.io/report/a9765a21685db2a8)