optimize-agent-prompt

[Skill Scanner] Instruction directing agent to run/execute external content All findings: [CRITICAL] command_injection: Instruction directing agent to run/execute external content (CI011) [AITech 9.1.4] [HIGH] skill_discovery_abuse: System prompt extraction attempt (SD002) [AITech 4.3] [HIGH] skill_discovery_abuse: System prompt extraction attempt (SD002) [AITech 4.3] This is documentation for designing an agent's system prompt and using Agent Context. It is internally consistent: the capabilities (prompt design, guidance for dataset vs system prompt) match the described actions. The only sensitive elements are expected: environment API keys and the exploration output file which the user must handle carefully. No evidence of obfuscated or malicious code, no download-execute patterns, no credential-harvesting behavior in the document itself. Recommend standard operational caution about handling API keys and avoiding pasting secrets into publicly visible documents.