Security Audit
frankxai/claude-skills-library:free-skills/loop-runner
github.com/frankxai/claude-skills-libraryTrust Assessment
frankxai/claude-skills-library:free-skills/loop-runner received a trust score of 85/100, 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 Arbitrary Command Execution via Untrusted Workspace Configuration.
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 20, 2026 (commit 93c4aad5). 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 | Arbitrary Command Execution via Untrusted Workspace Configuration The skill instructs the agent to read `.loop/<name>/LOOP.md` and execute 'every command in the charter's Verification section'. Since these files reside within the workspace, an untrusted repository or a malicious Pull Request could define arbitrary shell commands in the Verification section of `LOOP.md`, leading to arbitrary command execution when the loop runner is invoked. Avoid blindly executing commands defined in workspace configuration files. Require explicit user confirmation before executing any command retrieved from `.loop/<name>/LOOP.md`, or restrict execution to a pre-defined, safe set of commands. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/665dedfc99ae1f19)
Powered by SkillShield