ape-review-blog

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires quoting "the exact text" from the post in each finding, so if a draft contains API keys, tokens, passwords, or other secrets the LLM is forced to reproduce them verbatim in its output, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow is to review “the post” text and quote exact passages; if that post content is authored by an outsider (e.g., a blog draft submitted by someone other than the operating user), that outsider-authored free text is ingested into the LLM context for analysis and quoting.