linode-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill includes examples that embed personal access tokens and plaintext passwords directly in code and curl headers (e.g., token = "your-personal-access-token", Authorization: Bearer , root_pass: "secure_password_here"), which encourages including secret values verbatim in outputs and poses an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly pulls the OpenAPI specification from a public GitHub/raw content URL (see references/api.md and the line "The specification is automatically pulled from: https://github.com/linode/linode-api-docs" and https://raw.githubusercontent.com/linode/linode-api-docs/refs/heads/development/openapi.json), meaning the agent ingests third-party, public repository content which could contain untrusted, user-provided data.