Trust Assessment
hf-mem received a trust score of 78/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Shell Command Injection via Untrusted Model ID.
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 October 1, 2026 (commit 80f9fa53). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Shell Command Injection via Untrusted Model ID The skill instructs the agent to execute shell commands using 'uvx hf-mem' with user-provided parameters like '<model-id>' and '<file-or-path>' without instructing the agent to sanitize or validate these inputs. If a user provides a malicious model ID containing shell metacharacters (e.g., ';', '&&', '|', or backticks), it can lead to arbitrary command execution in the agent's environment. Instruct the agent to strictly validate the '<model-id>' and '<file-or-path>' parameters before executing the command. Ensure they only contain safe characters (e.g., matching '^[a-zA-Z0-9-_./]+$') and do not contain shell metacharacters. Alternatively, advise the agent to use safe APIs or escape the arguments properly. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/760c3429f2c02e0d)
Powered by SkillShield