job-posting-match

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

• Third-party content exposure detected (low risk: 0.10). The workflow searches and parses public job postings from third-party sites (JobKorea and Saramin) using search queries generated from user input, exposing the agent to outsider-authored job titles and descriptions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of an external npm package (@nomadamas/k-skill) from an unofficial GitHub-backed publisher during setup and runtime, representing a high-tier unverifiable runtime external dependency.