skill-quality-reviewer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires reading SKILL.md and other files and explicitly includes "Current" file content and YAML frontmatter verbatim in generated reports/improvement plans, which would cause any secrets present in those files to be output (exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow reads the target skill directory on disk (e.g., SKILL.md) and extracts its YAML/body text into the agent for analysis, so any insider prompt contents within the target skill are outsider-authored if the operating user didn’t author that skill.