contract-risk-analyzer-sneha-ganapavarapu

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime input is the user-pasted/uploaded contract text (an outsider-authored document), which the agent then reads and analyzes in LLM context; this is indirect prompt-injection exposure from the other party’s contract language.