{"skill":{"slug":"agent-firewall","displayName":"Agent Firewall","summary":"Real-time input/output filtering for agent communications. Block prompt injection, data exfiltration, and unauthorized commands before they reach the model.","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":85,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775253080558,"updatedAt":1775253108749},"latestVersion":{"version":"1.0.0","createdAt":1775253080558,"changelog":"Initial release of agent-firewall: real-time input/output filtering for agent communications.\n\n- Blocks prompt injections, data exfiltration, and unauthorized commands before reaching the model.\n- Includes layered input filters: injection detection, Unicode sanitization, encoding checks, rate/size limits, and role confusion detection.\n- Adds output filters: secret scanning, PII redaction, internal path scrubbing, malicious URL blocking, and consistency checks.\n- YAML-based configuration with clear, customizable rules for both input and output.\n- Built-in guardrails: append-only rules, logging for all blocks, human approval for rules deletion, and resistance to agent tampering.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"arhadnane","userId":"s17atsjv2c1a86fqvanj1x35as83yc1w","displayName":"Adnane Arharbi","image":"https://avatars.githubusercontent.com/u/14889338?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775253108749}}