Trust Assessment
apify-content-analytics 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 Shell Command Injection via unsanitized JSON_INPUT, Path Traversal via unsanitized output filename.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. The static_code_analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 11, 2026 (commit 0ea3e009). 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 | Shell Command Injection via unsanitized JSON_INPUT The skill instructs the agent to construct shell commands where the 'JSON_INPUT' for the '--input' argument is enclosed in single quotes. If the 'JSON_INPUT' (which is user-controlled) itself contains single quotes, it will break the shell command's quoting, allowing arbitrary shell commands to be injected and executed. For example, an input like `{"query": "'; rm -rf /; echo '"}` could lead to critical system compromise. The agent must properly escape all single quotes within the 'JSON_INPUT' string before embedding it into a shell command, or preferably, pass the JSON input via a safer method such as a temporary file or standard input to avoid shell injection vulnerabilities. | Unknown | SKILL.md:49 | |
| HIGH | Path Traversal via unsanitized output filename The skill instructs the agent to use a '--output' argument for the 'run_actor.js' script. The 'run_actor.js' script directly uses the value of this argument in 'writeFileSync' without any path sanitization or validation. If the agent allows user-controlled input for the output filename, a malicious user could specify a path like '../../../../etc/passwd' to write files to arbitrary locations on the filesystem, potentially overwriting critical system files or exfiltrating sensitive data. The agent should sanitize any user-provided output filename to prevent path traversal (e.g., by restricting it to a specific directory and disallowing '..' segments). Alternatively, the 'run_actor.js' script should implement robust path validation to ensure files are only written to an intended, secure directory. | Unknown | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/91081aa28d681a25)
Powered by SkillShield