Trust Assessment
wp-wpcli-and-ops 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 Potential Privilege Escalation via `--allow-root` flag.
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 June 1, 2026 (commit 9b1e542c). 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 | Potential Privilege Escalation via `--allow-root` flag The `wpcli_inspect.mjs` script parses an `--allow-root` argument from `process.argv` and passes it directly to the `wp` command. Running `wp-cli` as root is generally discouraged due to the potential for privilege escalation or system compromise if the WordPress installation or `wp-cli` itself has vulnerabilities. While the `SKILL.md` does not explicitly instruct the agent to use this flag, its presence in the script's argument parsing means a malicious prompt could instruct the agent to invoke the script with `--allow-root`, potentially leading to unintended root-level operations if the execution environment permits. Remove the `--allow-root` parsing and usage from the `wpcli_inspect.mjs` script unless there is a very specific, justified, and tightly controlled use case. If it must remain, ensure that the AI agent's invocation mechanism strictly disallows user-controlled `--allow-root` arguments for this skill. | Static | scripts/wpcli_inspect.mjs:10 |
Scan History
Embed Code
[](https://skillshield.io/report/49c5dd5cc507c08e)
Powered by SkillShield