ssrf

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract, save, and include "new credentials or tokens" (e.g., AWS keys, tokens) in the return summary and evidence files, which requires outputting secret values verbatim and thus poses a high exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Yes — the list is highly suspicious: it contains many localhost/internal IPs, cloud metadata endpoints, redirect/OOB domains and SSRF exploit vectors (r3dir.me, interactsh, metadata endpoints, attacker-controlled hosts) that are used to exfiltrate credentials, pivot to internal services, or deliver payloads.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is an explicit offensive SSRF exploitation guide that details techniques for data exfiltration (cloud metadata, local files), credential theft, remote code execution (gopher/dict/Redis/FastCGI), pivoting, and persistence—constituting deliberate malicious behavior.