panda-analytics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask users to paste their API key and to write that key verbatim into a ~/.pandas file (and to detect/save pasted keys), which requires the LLM to receive and embed secret values in commands/files, enabling secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches social-media analytics from a third-party service (Nosy Pandas) — e.g., SKILL.md’s "View social media analytics and insights via the Nosy Pandas API" and the numerous "API Call" curl examples to "$PANDAS_API_URL/analytics" — which ingests external (user-generated) social content that the agent reads and uses to produce recommendations/next actions.