hunt-source-leak

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's scripts explicitly search for, extract and print API keys, tokens, and plaintext secrets (via grep/python curl outputs and git-dumper/trufflehog), which would force an LLM-based agent to handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is an explicit offensive reconnaissance playbook for locating exposed source/build artifacts and extracting credentials, internal endpoints, and repository history—clearly intended to enable data exfiltration and unauthorized access.

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

• Third-party content exposure detected (low risk: 0.10). The workflow in SKILL.md performs discovery and then downloads/parses source maps and swagger from an external TARGET (e.g., /swagger.json, .js.map, and related JS bundles) and ingests their contents into runtime parsing/grep, which is free text authored by the outsider-controlled target application.