Dynamic code execution
Critical
- Finding
- Dynamic code execution detected.
Skill Security Scanner
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This appears to be a purpose-aligned security scanner, but its reports and optional VirusTotal use may expose code snippets, detected secrets, or file information if shared carelessly.
This skill is reasonable for scanning a specific skill directory, but treat its output as sensitive because it may include discovered secrets. Use a narrow skill_path, be cautious with HTML reports, and enable VirusTotal only when you are comfortable sharing the relevant file hashes or files with that provider.
Static analysis
Exposed secret literal
Critical
- Finding
- File appears to expose a hardcoded API secret or token.
Exposed secret literal
Critical
- Finding
- File appears to expose a hardcoded API secret or token.
Exposed secret literal
Critical
- Finding
- File appears to expose a hardcoded API secret or token.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
What this means
If pointed at a large or private directory, the tool may inspect and summarize files beyond the intended skill.
Why it was flagged
The scanner recursively reads files under the supplied path. This is necessary for scanning, but a broad path could include unintended local files.
Skill content
py_files = list(self.skill_path.rglob("*.py")) ... text_files = [f for f in self.skill_path.rglob("*") if f.is_file() ...]Recommendation
Run it only on the specific skill directory you intend to review, not on a home directory, system root, or unrelated private workspace.
What this means
Using this option gives the skill access to a VirusTotal API key and may consume that account's quota.
Why it was flagged
The skill accepts an optional VirusTotal credential, which is expected for its advertised provider integration.
Skill content
"name": "virustotal_api_key", "description": "Optional VirusTotal API key for file reputation scanning"
Recommendation
Use a dedicated VirusTotal key if needed, avoid sharing command logs containing the key, and rotate the key if it is exposed.
What this means
Generated JSON/HTML reports may contain sensitive code fragments or credentials from the scanned skill.
Why it was flagged
Detected secret lines are included as snippets in scan results, so real credentials found in scanned files may appear in reports or agent-visible output.
Skill content
message="Potential hardcoded secret detected", snippet=line.strip()[:80]
Recommendation
Treat scan reports as sensitive, redact secrets before sharing, and avoid committing generated reports to public repositories.
What this means
When enabled, file hashes or file data may be sent to an external provider, which can be sensitive for private or proprietary skills.
Why it was flagged
The documentation discloses optional use of an external VirusTotal service for file reputation checks.
Skill content
VirusTotal（可选） - 扫描技能包中的二进制文件和脚本 - 检查文件哈希信誉 - 需要 VT API key
Recommendation
Enable VirusTotal only for files you are comfortable checking with that service, and review the full implementation before using it on confidential code.