ClawAudit verdict
ydc-claude-agent-sdk-integration
Guides integration of Claude Agent SDK with You.com MCP; credential access is for API key configuration and packages are documented SDK dependencies.
⚠ 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.
Permission integrity
credential_access
package_install
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-you-api-key-here
Python os.getenv — reads environment variable
SKILL.md · prose · downgraded · os.getenv(
Accesses sensitive environment variables
SKILL.md · prose · downgraded · process.env.YDC_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
network_incredential_accesspackage_install Is this flag fair?
Thanks — recorded.