Trust Assessment
spidey received a trust score of 55/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unpinned Git Clone from External Repository, Potential Command Injection via Unsanitized User Argument in Configuration.
The analysis covered 4 layers: dependency_graph, manifest_analysis, llm_behavioral_safety, static_code_analysis. The static_code_analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 11, 2026 (commit 3572de0c). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unpinned Git Clone from External Repository The skill instructs the LLM to clone an external Git repository (`https://github.com/frankbria/ralph-claude-code.git`) without specifying a commit hash or tag. This means the content of the repository, including the `install.sh` script, can change at any time. A malicious update to the repository could introduce arbitrary code execution during the installation process, compromising the system where the skill is run. Pin the `git clone` command to a specific commit hash or tag (e.g., `git clone -b <tag_or_hash> ...`). Regularly review the upstream repository for security updates and update the pinned version accordingly. | Unknown | SKILL.md:201 | |
| HIGH | Potential Command Injection via Unsanitized User Argument in Configuration The skill instructs the LLM to generate a `.ralphrc` configuration file that includes `PROJECT_NAME="$ARGUMENTS"`. If the `$ARGUMENTS` variable (which comes directly from user input) contains shell metacharacters (e.g., `;`, `&`, `|`, `$(...)`), and if the `ralph` tool later processes this configuration file by sourcing it or executing its variables in a shell context without proper sanitization, it could lead to arbitrary command execution. The skill itself introduces this unsanitized user input into a configuration file intended for execution. Sanitize the `$ARGUMENTS` input before writing it to the `.ralphrc` file, ensuring that any shell metacharacters are properly escaped or removed. Alternatively, ensure that the `ralph` tool processes `PROJECT_NAME` as a literal string and not as an executable shell command. | Unknown | SKILL.md:220 |
Scan History
Embed Code
[](https://skillshield.io/report/6beb573ea29b6ea8)
Powered by SkillShield