kimi-integration
Verdict safe, but 2 findings (2 low), mainly policy violation, data exfiltration. Most recent scan 2026-02-06.
This skill is a legitimate configuration guide for integrating Kimi AI models into Clawdbot. The skill provides documentation and a connection testing script without any malicious behavior. The primary issues are minor documentation inconsistencies: a missing referenced file (different.py), and missing optional metadata fields. The test script (test_kimi_connection.sh) performs legitimate API connectivity tests using environment variables for credentials, which is the correct security practice. No prompt injection, data exfiltration, command injection, or other security threats were detected. The skill is SAFE for use, with only minor documentation improvements recommended.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Step-by-step guide for integrating Moonshot AI (Kimi) and Kimi Code models into Clawdbot. Use when someone asks how to add Kimi models, configure Moonshot AI, or set up Kimi for Coding in Clawdbot.
- Package
- 4 files, 18 KB
- SKILL.md
- 718 words, 12+ sections
- Code
- Shell (1)
SKILL.md covers: Kimi Model Integration · Overview · Prerequisites · Getting API Keys · Moonshot AI (Kimi K2) · Kimi Code · Integration Steps · Option 1: Moonshot AI (Kimi K2 models) · Option 2: Kimi Code (specialized coding model) · Using Both Providers · Troubleshooting · Model not appearing in list
Findings
LOW Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
LOW Missing Referenced File: different.py Data Exfiltrationllm
The SKILL.md instructions reference a file 'different.py' that is not included in the skill package. This could indicate incomplete packaging, a documentation error, or potentially a missing malicious component. However, since the file is not present and cannot be analyzed, this represents a minor documentation inconsistency rather than an active threat.
Referenced file 'different.py' mentioned in instructions but not found in packageWhat is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 3.8 KB |
SKILL.md | doc | 6.3 KB |
references/config-examples.md | doc | 5.7 KB |
scripts/test_kimi_connection.sh | script | 1.9 KB |
External hosts referenced
api.moonshot.cn api.kimi.com platform.moonshot.cn docs.clawd.bot
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
MOONSHOT_API_KEY KIMICODE_API_KEY
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/kimi-integration
- Raw scan result: kimi-integration-scan.json
- Badge for your README:
- Request a re-scan