find-companies-posting-about-specific-things

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to prompt for and then embed a user verification code and email verbatim into shell commands (e.g., bash "$SIGNUP" verify "<user_email>" "<code>"), which requires the LLM to handle secrets directly even though API keys are meant to be stored by scripts—this matches insecure patterns of embedding sensitive values in generated commands.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly deploys and queries a social-listening agent (see SKILL.md steps using bash "$API" POST /api/v1/signal/deploy/social-listening-agent and subsequent POST /api/v1/signal calls to https://api.openfunnel.dev) to scan and present public social-media posts and matched accounts/people — untrusted, user-generated third-party content that the agent reads and uses to drive deployments and decisions.