mobile-pentest

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content contains explicit, actionable techniques for SSL‑pinning bypass, credential/keychain extraction, data exfiltration to attacker-controlled endpoints, remote command execution via WebView/Intents, and methods to hide root/jailbreak—all high‑risk, dual‑use behaviors easily repurposed for malicious attacks.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and interpreting public, untrusted third‑party content (e.g., "curl https://app-name.firebaseio.com/.json" under "Firebase / Cloud Misconfig", "aws s3 ls s3://bucket-name --no-sign-request", and deep‑link/WebView examples loading attacker-controlled URLs), and the workflow expects the operator/agent to read those responses and perform follow-up actions, so external content could materially influence behavior.