mitm-find-callback

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the agent to analyze a mitmproxy traffic dump (log.txt) for callbacks and produce exploit tests/parameters, which will typically require extracting and embedding verbatim hashes, salts, tokens, or cookies from the logs—posing a secret exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires analyzing a mitmproxy dump file (log.txt) captured via mitmdump (network traffic), which is untrusted third-party content the agent must read and use to generate findings and tests, so it could contain malicious/instructional payloads that influence behavior.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill is explicitly focused on payment systems and shows concrete, actionable methods to alter payment callbacks (e.g., curl POSTs that change status, tamper with hashes, and modify amounts). Its primary purpose is testing/exploiting payment callback/webhook handling and includes exact request examples to manipulate transaction outcomes (free orders, refunds). That is a specific capability to execute/alter financial transactions rather than a generic tool, so it meets the "direct financial execution" criterion.