arize-trace

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to prompt for an Arize API key if missing, echoes environment variables that reveal ARIZE_API_KEY, and directs writing the API key verbatim into ~/.arize/config.toml, which requires handling and outputting secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and read span/trace data from Arize via the ax CLI (e.g., "ax spans export" / "ax traces export" in SKILL.md) and to inspect fields like attributes.llm.input_messages, attributes.output.value, and attributes.retrieval.documents.contents, which are untrusted, user-generated third‑party content that could contain instructions influencing subsequent actions.