python-sdk

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes examples that hard-code API keys and webhook URLs (e.g., api_key="inf_your_key", api_key="inf_...", and a Slack webhook), which encourages embedding secret values verbatim in code/output and therefore creates an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This content contains high-risk patterns: direct use of eval on external input (enabling remote code execution), automatic upload of local file paths and examples sending local file bytes (facilitating data exfiltration), and webhook/secret usage that can be abused to send sensitive data to external endpoints.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill manifest includes a skill entry that points to an external URL ("https://example.com/skills/api-docs.md") which would be fetched at runtime to provide agent skill content that directly influences prompts/context.