skill-maintainer

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads upstream repository contents (SKILL.md files) from GitHub via curl during checks and automated sync workflows, which are outsider-controlled code/content sources.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches files via GitHub API and raw content URLs (api.github.com and raw.githubusercontent.com) at runtime to check upstream drift, but these are uncontrolled external endpoints without enforced verification digests or strong cryptographic provenance, representing a high-tier risk.