drawio-skill

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

• Third-party content exposure detected (high risk: 0.70). The skill's required Step 0 "Update check" calls out a git ls-remote against the upstream origin and may run git pull (SKILL.md Step 0), which fetches and can ingest code from a public upstream repository that could change the skill's runtime behavior—i.e., untrusted third‑party content that can influence decisions and tool use.