Trust Assessment
molt-security-auditor received a trust score of 63/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 2 high, 1 medium, and 1 low severity. Key findings include Missing required field: name, Arbitrary Network Request Capability (SSRF Potential), Denial of Service via Resource Exhaustion from Large Untrusted Input.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 68/100, indicating areas for improvement.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary Network Request Capability (SSRF Potential) The `fetchSkill` function makes an `https.get` request to a URL provided directly from `process.argv[2]`. This allows the skill to make arbitrary outbound network requests to any external or potentially internal (via Server-Side Request Forgery - SSRF) endpoint. This broad network access can be abused to fetch malicious payloads, probe internal network resources, or participate in denial-of-service attacks. Implement strict URL validation (e.g., whitelist allowed domains/protocols, prevent internal IP ranges). Consider sandboxing network access or requiring explicit user confirmation for external requests. | LLM | audit.js:6 | |
| HIGH | Denial of Service via Resource Exhaustion from Large Untrusted Input The `powHash` function performs a Proof-of-Work calculation on `content + Date.now()`, where `content` is fetched from an arbitrary URL provided by the user. If an attacker provides a URL pointing to an extremely large file, the repeated hashing of this large string within a `while(true)` loop can consume excessive CPU and memory resources, leading to a denial of service for the skill's execution environment. Implement size limits for fetched content. Before passing content to `powHash`, check its size and reject excessively large inputs. | LLM | audit.js:28 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/kunoiiv/molt-security-auditor/SKILL.md:1 | |
| LOW | Uncontrolled Local File Write The skill writes a file named `chain.json` to the current working directory using `fs.writeFileSync`. While the content written is controlled by the skill and not directly from untrusted input, writing files to arbitrary locations in the filesystem can be an excessive permission, potentially leading to overwriting existing files or consuming disk space if the skill were to be modified to write larger or more frequent files. If file writing is necessary, ensure it's done in a sandboxed environment or to a user-specified, controlled location. Consider if the output can be returned directly instead of written to a file. | LLM | audit.js:30 |
Scan History
Embed Code
[](https://skillshield.io/report/14408d988bf7e1c7)
Powered by SkillShield