wiki-update

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires reading and quoting exact page and source text (including frontmatter and pasted sources) and showing diffs/edits verbatim, so if those files contain API keys or secrets the LLM would be forced to output them, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow (Parameters and Step 2) explicitly says that for --reason new-source it will read the new source "file, URL, or paste" and then use that content to produce edits and sweep related pages, so arbitrary external URLs (untrusted third‑party content) are ingested and can materially influence the agent's edits and actions.