ClawAudit verdict

yandexgpt

yandexgpt-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill provides an OpenAI-compatible translation proxy for YandexGPT without exhibiting malicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

40
security
100
transparency
90
maintenance

Findings (5)

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · frontmatter · ~/.openclaw/openclaw.json

Pattern match high

Possible hardcoded credential

scripts/patch-config.sh · prose · downgraded · apiKey: 'not-needed

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

src/proxy.js · prose · downgraded · http://127.0.0.1

Pattern match low

Node http/https module — low-level network access

src/proxy.js · prose · downgraded · require("http")

Pattern match low

Accesses sensitive environment variables

src/proxy.js · prose · downgraded · process.env.YANDEX_API_KEY

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: YANDEX_API_KEY). Requires 2 system binaries. (1 elevated: curl).

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API