pica-actions

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires embedding a connectionKey (a token-like secret shown by pica connection list) directly into generated pica actions execute commands, forcing the LLM to handle and output secret values verbatim.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to use the Pica CLI to search actions, retrieve action "knowledge", and execute API calls against 200+ third-party platforms (e.g., "send an email via Gmail", "list my Shopify orders", "fetch my calendar events"), which means the agent will fetch and interpret untrusted/user-generated content from external APIs that can materially influence which actions are taken.