Security Audit

JThomasDevs/kalshi-agent:root

github.com/JThomasDevs/kalshi-agent

AI SkillCommit 1af9b54c9ade

CRITICAL

Scanned 12 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

JThomasDevs/kalshi-agent:root 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: 3 critical, 0 high, 3 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Persistence mechanism: Shell RC file modification, Sensitive environment variable access: $HOME.

The analysis covered 4 layers: dependency_graph, llm_behavioral_safety, manifest_analysis, static_code_analysis. The manifest_analysis layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on February 8, 2026 (commit 1af9b54c). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

40%

Static Code Analysis

79%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

4 findings

Shell Execution

6 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings6

Severity	Finding	Layer	Location
CRITICAL	Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles.	Unknown	/tmp/skillscan-clone-6pus16aa/repo/SKILL.md:12
CRITICAL	Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles.	Unknown	/tmp/skillscan-clone-6pus16aa/repo/install.sh:46
CRITICAL	Dynamic Code Loading via External Git Clone The installation script downloads the skill's core logic from an external GitHub repository at runtime. This 'dropper' behavior bypasses static security analysis, as the actual code being executed is not present in the skill package. Furthermore, the script pulls the latest version (unpinned), meaning the code can change at any time, introducing a severe supply chain risk. Bundle the source code within the skill package. Do not rely on runtime `git clone`. If external code is required, use a package manager with pinned versions/hashes or pin the git repository to a specific commit hash.	Unknown	install.sh:12
MEDIUM	Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration.	Unknown	/tmp/skillscan-clone-6pus16aa/repo/SKILL.md:12
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Unknown	/tmp/skillscan-clone-6pus16aa/repo/install.sh:26
MEDIUM	Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration.	Unknown	/tmp/skillscan-clone-6pus16aa/repo/install.sh:46

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5aeab2d69a98d670.svg)](https://skillshield.io/report/5aeab2d69a98d670)