Exposed secret literal
Critical
- Finding
- File appears to expose a hardcoded API secret or token.
Openclaw Search Pro
Security checks across static analysis, malware telemetry, and agentic risk
Overview
Prompt-injection indicators were detected in the submitted artifacts (base64-block, unicode-control-chars); human review is required before treating this skill as clean.
Install only if you want a networked web-search/content-extraction tool. Be aware that search terms and requested URLs go to external services, and store any optional API keys carefully. ClawScan detected prompt-injection indicators (base64-block, unicode-control-chars), so this skill requires review even though the model response was benign.
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.
Obfuscated code
Warn
- Finding
- Potential obfuscated payload detected.
Obfuscated code
Warn
- Finding
- Potential obfuscated payload detected.
Obfuscated code
Warn
- Finding
- Potential obfuscated payload detected.
Obfuscated code
Warn
- Finding
- Potential obfuscated payload detected.
Obfuscated code
Warn
- Finding
- Potential obfuscated payload detected.
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
Search queries and URLs you ask it to process may be sent over the network and fetched by local scripts.
Why it was flagged
The skill documents local script execution and fetching arbitrary user-supplied URLs, which is normal for this search/extraction purpose but worth noticing.
Skill content
python3 search-pro/scripts/multi-search.py "OpenClaw 技能开发" ... python3 search-pro/scripts/extract.py --url https://example.com
Recommendation
Use it for non-sensitive searches, and avoid extracting URLs you do not want your machine to contact.
What this means
If you configure API keys, the skill can use those provider accounts for searches and may store keys in a local config file.
Why it was flagged
Optional provider credentials are documented and purpose-aligned, but registry metadata does not declare required credentials because they are optional.
Skill content
export TAVILY_API_KEY="your-key" ... "api_key": "your-key" ... API Key 存储在 `config/search-config.json`
Recommendation
Prefer environment variables where possible, restrict file permissions, and only add API keys for providers you intend to use.
What this means
An English-speaking user might underestimate that searches and URL fetches contact external services.
Why it was flagged
This English documentation conflicts with SKILL.md, which says search queries are sent to configured search engines; the conflict could confuse users about data flow.
Skill content
Scripts run locally - No network calls (unless specified) ... No upload - No data sent to external servers
Recommendation
Treat this as a networked search tool despite the README_EN wording, and review queries/URLs before using it.
What this means
Installing dependencies can run package-manager behavior and brings third-party code into the skill directory.
Why it was flagged
The README includes a user-directed dependency install step, and the package bundles many Node dependencies; this is expected for the Node.js implementation but adds supply-chain surface.
Skill content
cd ~/.openclaw/workspace/skills/search-pro npm install
Recommendation
Install from a trusted source, review package metadata if needed, and avoid running global install unless you want system-wide commands.