rsa-attack-techniques

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The playbook's examples and workflows explicitly compute and print secret material (private keys, factors, decrypted plaintext) so an agent following it would need to handle and output secret values verbatim, creating exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is an explicit RSA attack playbook (detailed exploit techniques, scripts, and tool usage) that enables active cryptographic attacks — a high-risk, dual‑use capability — even though it contains no hidden backdoor, exfiltration routine, or obfuscated payloads.

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 the agent to consult public resources such as factordb.com (see the Decision Tree and Tools sections) to check if a modulus is already factored, meaning the agent is expected to fetch and act on untrusted, public third‑party content as part of its workflow.