ai-patterns

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

• Third-party content exposure detected (low risk: 0.10). The required workflow clones or pulls a public GitHub repository containing developer reference patterns into local cache and reads markdown documents from it.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes a script that clones a GitHub repository (https://github.com/lexler/augmented-coding-patterns) at runtime to populate required documentation and pattern definitions used by the skill, representing a common/reputable unofficial operational dependency.