Trust Assessment
anki-connect received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via Shell Tool Execution.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 326f2466). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Command Injection via Shell Tool Execution The skill explicitly instructs the agent to execute shell commands using `curl` and `jq` to interact with the AnkiConnect API. While the provided examples demonstrate best practices for embedding user-controlled data into JSON payloads using `jq --arg` and piping to `curl -d @-`, the general instruction to 'run them via curl/jq (or equivalent tools)' introduces a risk of command injection. If the agent constructs any part of the shell command (e.g., arguments to `curl` or `jq`, or the `query` string before it's passed to `--arg`) using unsanitized user input, it could lead to arbitrary command execution. The rubric does not provide explicit guidance on sanitizing all user input that might influence shell command construction. Instruct the agent to rigorously sanitize and escape all user-controlled input before incorporating it into any part of a shell command. Specifically, ensure that any user-provided strings used as arguments to `curl` or `jq` (beyond the JSON payload itself) are properly quoted or escaped to prevent shell metacharacter interpretation. Add explicit guidance on input sanitization for all user-derived shell command components. | Unknown | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/06d894d2d19f4647)
Powered by SkillShield