Trust Assessment
safety-checker received a trust score of 81/100, 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 Shell command injection via `jq` validation, Unpinned dependency in installation instructions.
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 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 | Shell command injection via `jq` validation The `scripts/safety-checker.sh` script uses `jq empty` to validate user-provided JSON input. If the `$INPUT` variable contains shell metacharacters (e.g., `'; rm -rf /'`), these characters could be interpreted by the shell before `jq` is executed, leading to arbitrary command execution. This allows an attacker to inject and execute arbitrary shell commands. Use a safer method for JSON validation that prevents shell metacharacter interpretation. For example, use `printf '%s' "$INPUT" | jq -e . >/dev/null` which will exit with a non-zero status if the input is not valid JSON, and `printf` is safer than `echo` for arbitrary strings. | LLM | scripts/safety-checker.sh:19 | |
| MEDIUM | Unpinned dependency in installation instructions The installation instructions for `clawhub` in `SKILL.md` use `@latest` (e.g., `npx clawhub@latest install safety-checker`). This means that each time the command is run, the latest version of `clawhub` will be downloaded and executed. This introduces a supply chain risk as a malicious update to `clawhub` could be automatically pulled and executed without explicit user review, potentially compromising the system. Pin the `clawhub` dependency to a specific version (e.g., `npx clawhub@1.2.3 install safety-checker`) to ensure deterministic and reviewable installations. Users should be encouraged to verify the integrity of specific versions. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/04c46124155060b5)
Powered by SkillShield