Trust Assessment
git-pushing received a trust score of 62/100, 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 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, User-controlled input allows command substitution leading to arbitrary code execution.
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 12, 2026 (commit 458b1186). 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 | User-controlled input allows command substitution leading to arbitrary code execution The `smart_commit.sh` script assigns the first argument (`$1`) directly to the `MESSAGE` variable using `MESSAGE="${1:-chore: update code}"`. If a malicious user provides input containing command substitution (e.g., `$(rm -rf /)` or `` `evil_command` ``), the shell will execute these commands *before* assigning the value to `MESSAGE`. This allows for arbitrary command execution on the agent's host. The `SKILL.md` instructs the host LLM to pass user input as an argument to this script, creating a direct exploit path. User-provided input must be sanitized or escaped to prevent command substitution before being passed to shell scripts. The host LLM should escape user input using a method like `printf %q` when constructing shell commands. Alternatively, the script itself could read the commit message from standard input (e.g., `git commit -F -`) to avoid shell interpretation of the message content as an argument. | LLM | scripts/smart_commit.sh:3 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/9e469ebe0e0eec33)
Powered by SkillShield