Trust Assessment
hergunmac received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection via Dynamic External Instructions.
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 February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection via Dynamic External Instructions The skill instructs the LLM to fetch and interpret a 'live context file' (`https://www.hergunmac.com/llm.txt`) for 'up-to-date URL patterns, UI elements, and browser automation notes.' This external file is untrusted and can be modified at any time by the remote server. An attacker who compromises `hergunmac.com` could inject malicious instructions into `llm.txt`, leading to prompt injection, data exfiltration, or other arbitrary actions by the LLM. The explicit mention of 'browser automation notes' indicates the content will be interpreted as executable instructions, making this a critical vector for manipulating the host LLM. Remove the instruction to fetch and interpret dynamic external content. All instructions and context for the LLM should be bundled directly within the skill package to ensure integrity and prevent remote manipulation. If dynamic updates are absolutely necessary, implement a robust signing and verification mechanism for the external content. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/3fdc9a43170623ef)
Powered by SkillShield