Trust Assessment
research received a trust score of 41/100, 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: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Command Injection via output_file 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 13, 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/research-2/SKILL.md:10 | |
| 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/research-2/SKILL.md:10 | |
| HIGH | Command Injection via output_file argument The `scripts/research.sh` script directly uses the second command-line argument (`$2`, assigned to `OUTPUT_FILE`) in a shell redirection (`> "$OUTPUT_FILE"`) without proper sanitization or escaping. An attacker can inject shell metacharacters (e.g., `;`, `|`, `&`, `$(...)`) into the `output_file` argument to execute arbitrary commands on the system where the script is run. For example, providing `'; rm -rf /'` as the `output_file` would lead to the deletion of files. Sanitize the `OUTPUT_FILE` variable to remove or escape shell metacharacters, or use a safer method for writing to a user-specified file. A robust solution involves using `tee` with the `--` option to prevent options injection, e.g., `echo "$RESPONSE" | tee -- "$OUTPUT_FILE" > /dev/null`. Alternatively, strictly validate the filename against a whitelist of allowed characters (e.g., alphanumeric, hyphens, underscores, dots, slashes for paths) before use. | LLM | scripts/research.sh:50 |
Scan History
Embed Code
[](https://skillshield.io/report/4a6d5327f63c89e0)
Powered by SkillShield