Trust Assessment
crawl received a trust score of 27/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Command Injection and Path Traversal via output_dir argument.
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 February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/barneyjm/crawl/SKILL.md:10 | |
| CRITICAL | Command Injection and Path Traversal via output_dir argument The `scripts/crawl.sh` script directly uses the second command-line argument (`$2`), intended for `output_dir`, in a `mkdir -p "$OUTPUT_DIR"` command without proper sanitization or validation. An attacker can inject shell metacharacters (e.g., `;`, `|`, `&`, `$(...)`) into this argument to execute arbitrary commands on the system where the skill is run. Additionally, by providing path traversal sequences (e.g., `../../`), an attacker could write crawled files to arbitrary locations outside the intended output directory. Sanitize the `OUTPUT_DIR` variable to prevent shell metacharacters and path traversal sequences. This can be done by validating the input against a strict whitelist of allowed characters (e.g., alphanumeric, hyphens, underscores) and ensuring it does not contain path separators or `..` sequences. Alternatively, use a more robust method for creating directories that does not involve direct shell expansion of untrusted input, or ensure the output directory is always created within a securely controlled base path. | LLM | scripts/crawl.sh:60 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/barneyjm/crawl/SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/08e31c237a3864dc)
Powered by SkillShield