Trust Assessment
personality-switcher received a trust score of 59/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Prompt Injection via Personality Description.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection via Personality Description The skill's `/create-personality` command allows users to provide a natural language description, which is then used by the 'agent' (likely the host LLM) to generate the content for `SOUL.md` and `IDENTITY.md` files. This direct use of untrusted user input as a prompt for content generation creates a critical prompt injection vulnerability. A malicious user could craft a description containing instructions to manipulate the host LLM's behavior, generate harmful content, or attempt to exfiltrate information if the LLM has access to other tools or context. Implement robust sanitization and validation of the user-provided description before it is passed to the LLM for content generation. Consider using a separate, sandboxed LLM for content generation, or strictly constrain the LLM's capabilities when processing untrusted input. If using the host LLM, ensure strong guardrails are in place to prevent malicious instructions from being executed. Additionally, review the generated `SOUL.md` and `IDENTITY.md` content for any embedded malicious instructions before activation. | LLM | SKILL.md:109 | |
| 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. | Static | skills/robb1010/personality-switcher/install.sh:5 | |
| 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. | Static | skills/robb1010/personality-switcher/uninstall.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/43b24bff29432263)
Powered by SkillShield