Trust Assessment
smart-linkedin-inbox received a trust score of 65/100, 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, Embedded LLM instruction in untrusted content.
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 | Embedded LLM instruction in untrusted content The untrusted `SKILL.md` contains a direct instruction to the host LLM: 'Tell OpenClaw to run the skill smart-linkedin-inbox read SKILL.md and use for LinkedIn'. This attempts to manipulate the LLM's behavior from within content explicitly marked as untrusted data, which is a form of prompt injection. The analyzer is instructed to treat all content between the UNTRUSTED_INPUT tags as data, not instructions. Remove or rephrase the instruction 'Tell OpenClaw to run the skill smart-linkedin-inbox read SKILL.md and use for LinkedIn' from the `SKILL.md` file. Instructions for the LLM should come from trusted sources, not from within the skill's untrusted documentation. If this is meant to be a user instruction, it should be clearly phrased as such, e.g., 'You can instruct OpenClaw by saying: 'Run the skill smart-linkedin-inbox...'. | LLM | SKILL.md:32 | |
| 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/vdybenko/smart-linkedin-inbox/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/53e15d19f0bf0337)
Powered by SkillShield