Trust Assessment
clawprint-verify received a trust score of 82/100, 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 Command Injection via CLAWPRINT_SERVER_URL, JSON Injection via user-supplied arguments.
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 14, 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 | Command Injection via CLAWPRINT_SERVER_URL The `CLAWPRINT_SERVER_URL` environment variable is directly used within double quotes in `curl` commands. If this variable contains shell command substitutions (e.g., `$(evil_command)` or backticks), the embedded command will be executed by the shell before `curl` is invoked. This allows an attacker to execute arbitrary commands by manipulating the `CLAWPRINT_SERVER_URL` environment variable. Strictly validate the format of `CLAWPRINT_SERVER_URL` to ensure it is a well-formed URL and does not contain shell metacharacters or command substitutions. Alternatively, use a more robust method for constructing the `curl` command that prevents shell expansion of the URL variable. | LLM | clawprint-challenge.sh:30 | |
| MEDIUM | JSON Injection via user-supplied arguments The `challenge_id` and `answer` arguments, which are user-supplied, are directly embedded into JSON payloads without proper escaping of JSON special characters (like `"` or `\`). An attacker could craft these arguments to inject arbitrary JSON fields into the request body, potentially altering the intended API call or bypassing server-side logic if the backend is not robustly handling unexpected JSON structures. While not a direct shell command injection, it represents an injection vulnerability that could lead to API abuse or data manipulation. Escape JSON special characters in user-supplied arguments (`challenge_id`, `answer`) before embedding them into the JSON string. A common and safer approach is to use `jq` to construct the JSON payload, as `jq` handles proper JSON escaping automatically. For example, `jq -n --arg id "$challenge_id" --arg ans "$answer" '{"challenge_id": $id, "answer": $ans}'`. | LLM | clawprint-challenge.sh:93 |
Scan History
Embed Code
[](https://skillshield.io/report/b654e01f987b96ce)
Powered by SkillShield