submit-program

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks users to provide an affiliate link ("affiliate_link") and indicates it may be included/verified in the listing, which can require the agent to parse and echo the full link (including tracking tokens) verbatim — exposing potentially sensitive affiliate tokens.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md requires runtime web research via web_search of official affiliate/network/pricing pages (public web content), which can include outsider-authored free text that the agent would ingest into the LLM context.