vulnhunter-security-scanner

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

• Third-party content exposure detected (high risk: 0.85). The required workflow can clone and scan target repositories specified at runtime (e.g., vulnhunter-agent clones targets[].url), so the agent will ingest outsider-authored repository source text into the LLM context for analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The repository https://github.com/capitalone/vulnhunter.git is cloned during installation/CI and then installed/run (pip install / python -m), so remote code and prompt/phase files from that repo are fetched at runtime and directly control the agent's prompts/execution.