Trust Assessment
endpoints 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 3 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Arbitrary Local File Read and Exfiltration, API Key Transmitted to External Service.
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 | Arbitrary Local File Read and Exfiltration The `scanFile` function reads the content of any local file specified by the `filePath` argument and then sends this content to an external API (`https://endpoints.work/api/scan`). This allows an attacker to instruct the agent to read sensitive files from the local filesystem (e.g., configuration files, SSH keys, password files) and exfiltrate their contents to a third-party service. Restrict the `filePath` argument to a predefined, safe directory or a specific set of allowed file types. Implement robust input validation to prevent path traversal attacks. If the skill's purpose requires scanning arbitrary files, ensure explicit user consent and clear warnings are provided before accessing local files, and consider sandboxing the file access. | LLM | scripts/src/index.ts:209 | |
| MEDIUM | Unpinned npm dependency version Dependency 'dotenv' is not pinned to an exact version ('^16.3.1'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/adamkristopher/endpoints/scripts/package.json | |
| INFO | API Key Transmitted to External Service The skill loads `ENDPOINTS_API_KEY` from environment variables and includes it as a Bearer token in the `Authorization` header for all requests to `https://endpoints.work`. While this is standard practice for API authentication, it means the API key is transmitted over the network to a third-party service. If the `API_URL` environment variable could be manipulated by an attacker, this could lead to credential harvesting. However, `API_URL` is an environment variable, not directly user-controlled. Ensure that the `ENDPOINTS_API_URL` environment variable is immutable and cannot be altered by untrusted input. Implement strict access controls for the environment where the skill runs to prevent unauthorized modification of environment variables. | LLM | scripts/src/index.ts:100 |
Scan History
Embed Code
[](https://skillshield.io/report/24b3df8f9bfa6820)
Powered by SkillShield