skill-fit

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads external SKILL.md frontmatter when catalog.yaml is absent (line 56), which is considered low-risk community/package registry inspection since it involves fetching/scanning specific untrusted skill files upon execution.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions to make unauthenticated REST API requests to external domains (api.skillhub.cn and skills.sh) during runtime fallback checks, constituting a weak/unknown external operational dependency.