github-project-contributor-finder-api-skill

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and the script scripts/github_project_contributor_finder_api.py call the BrowserAct workflow API to traverse and extract GitHub repository and contributor profiles (public, user-generated content on GitHub and linked personal sites), which the agent ingests and uses to drive decisions like contacting or ranking contributors.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes a remote workflow at runtime via the BrowserAct API (https://api.browseract.com/v2/workflow), which executes server-side workflow logic (TEMPLATE_ID) that the skill depends on to produce its outputs, so the fetched remote workflow effectively runs code and controls the agent's behavior.