outbox-publish

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). High risk: the skill explicitly instructs the agent to accept/store/validate API keys (used in Authorization headers) and to display generated plaintext keys "ONE TIME", which requires handling and at times outputting secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and processes user-generated HTML from public/unlisted/private Outbox URLs (see Flow 2 "GET https://out-box.dev/u/:user/:slug" and Flow 3 "read-modify-write" where the agent parses and acts on that HTML), which is untrusted third-party content that can directly influence the agent's subsequent actions.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)