llm-prompt-injection

This is a coherent offensive security playbook rather than a deceptive skill: its content matches its stated purpose, and it does not install software or directly exfiltrate data. However, it equips an AI agent with high-risk prompt-injection and tool-abuse techniques, so it should be treated as a high-risk security-testing skill, not malware.

No evidence of traditional malware or supply-chain compromise exists in this module because it contains no executable behavior, I/O, networking, or credential/process access. However, the file is a highly actionable jailbreak/prompt-injection techniques catalog (including system-prompt extraction and escalation/encoding bypass patterns). Its primary risk is enabling abusive instruction crafting and increasing the likelihood of safety bypasses in downstream LLM deployments, especially if included in applications that generate or validate prompts.