Trust Assessment
linkedin-cli received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Reliance on Highly Sensitive Session Cookies, Unpinned Third-Party Dependency.
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 | |
|---|---|---|---|---|
| HIGH | Reliance on Highly Sensitive Session Cookies The skill requires the user to provide `li_at` and `JSESSIONID` session cookies via environment variables. These cookies grant full access to the user's LinkedIn account. While the script correctly retrieves them from environment variables and does not appear to exfiltrate them, the inherent risk associated with handling such powerful, long-lived credentials is high. A compromise of the environment where these variables are stored would lead to complete account takeover. Educate users about the significant risks of exposing these session cookies. Recommend storing them in secure secrets management systems or using short-lived credentials if possible. Explore if the `linkedin-api` library or LinkedIn itself offers alternative, less sensitive authentication methods (e.g., OAuth with limited scopes and refresh tokens) that could reduce the impact of a credential compromise. | LLM | scripts/lk.py:15 | |
| MEDIUM | Unpinned Third-Party Dependency The `SKILL.md` instructs users to install the `linkedin-api` Python package without specifying a version. This practice can lead to supply chain vulnerabilities, as future updates to the `linkedin-api` package could introduce breaking changes, bugs, or even malicious code without the skill developer's explicit review. This makes the skill's behavior non-deterministic and potentially insecure over time. Pin the version of the `linkedin-api` package in the installation instructions (e.g., `pip install linkedin-api==X.Y.Z`) or provide a `requirements.txt` file. This ensures that users install a known, tested, and secure version of the dependency, improving the skill's stability and security posture. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/6299dc5f22d6d36c)
Powered by SkillShield