retry-utils

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows running arbitrary shell commands (e.g., "curl https://api.example.com/data") and documents options like --until-pattern and --stop-on that cause the tool to read and act on command stdout/stderr, which means untrusted public web content can be fetched and directly influence retry/decision logic.