llm-prompt-injection

SUSPICIOUS: the skill is internally consistent as an LLM security testing playbook, but its actual footprint is an offensive technique library for jailbreaks, system-prompt extraction, tool abuse, and data exfiltration. There is no installer or credential-harvesting binary, so this is not confirmed malware, but it is a high-risk AI-agent exploit skill.

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.