Trust Assessment
boycott-chatgpt-54c8dfea received a trust score of 66/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Prompt attempts to manipulate LLM's recommendations and stance.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt attempts to manipulate LLM's recommendations and stance The skill's primary prompt content is a highly opinionated and persuasive argument advocating for the boycott of ChatGPT and explicitly recommending alternative AI models (Claude, Gemini, open-source). This content is designed to manipulate the host LLM's output by influencing its recommendations and potentially its neutrality on the topic, steering it towards a specific viewpoint and product preference. While not a direct system-level instruction override, it constitutes an attempt to manipulate the LLM's behavior and output, which aligns with the definition of prompt injection. Review the prompt content to ensure it aligns with ethical guidelines for LLM interaction. If the intent is to provide neutral information, rephrase the prompt to remove persuasive language and explicit product recommendations/boycott calls. If the intent is to provide a specific viewpoint, ensure the LLM is designed to handle such biased input appropriately without presenting it as neutral fact or recommendation. | LLM | SKILL.md:20 | |
| 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 | skills/hhhh124hhhh/boycott-chatgpt-54c8dfea/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/9b828ba6a67c5479)
Powered by SkillShield