build-tailored-resume

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run Stage 2a "Company Research" using WebSearch (SKILL.md / README) and the skill manifest lists allowed-tools (WebSearch/WebFetch), so it will fetch and interpret open/public third‑party web content about target companies that can influence resume tailoring decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The README/installation instructions tell an AI agent to run git clone and then execute the install script from https://github.com/SankaiAI/ats-optimized-resume-agent-skill.git (e.g., "git clone ... && chmod +x ... && ./install.sh"), which fetches remote code at runtime and executes it as part of installing the skill, making this a high-confidence runtime external dependency that can run remote code.