Suspicious: agent - guard-signals.mjs | Skillgate

Skillgate scanned guard-signals.mjs in agent and rated it Suspicious with a risk score of 62/100 (12 detections).

Skillgate found behaviour that needs a human decision: it may be a legitimate but powerful pattern, or an attack. Review the flagged lines in the source before installing.

What was found

• SG-004 Policy Override - CRITICAL (2x): Patterns that instruct the AI to ignore guidelines or take a new persona
• SG-063 Anti-LLM-Scanner Directive - CRITICAL: Adversarial strings designed to suppress AI-driven static analysis (auto-promotes flag to malicious)
• SG-018 Memory Poisoning - HIGH: Writes to CLAUDE.md or ~/.claude/memory to persist malicious instructions across sessions
• SG-019 Environment Probing - HIGH: System enumeration commands: whoami, uname, env dump, process listing, cloud IMDS probes
• SG-060 IDE Auto-Approval / YOLO - HIGH: autoApprove, runOn folderOpen, permission_mode bypass, --yolo, --dangerously-skip-permissions
• SG-010 Obfuscation: Unicode - MEDIUM (2x): Zero-width characters and RTL override characters
• SG-022 Context Window Flooding - MEDIUM: Repetitive filler text, context boundary spoofing, excessive separators
• SG-097 Fetch-and-Execute - MEDIUM: Network-fetched content executed as code (pipe-to-shell, process substitution, eval, render-then-run, download-then-run)
• SG-098 Agent Safety-Control Suppression - MEDIUM: Instruction to suppress safety warnings, skip confirmation, or hide actions from the user
• SG-017 External MCP Server - LOW: MCP server URLs pointing outside localhost

What to do

Read the flagged lines in the source file yourself before installing it or letting an agent load it. Every detection above links to the rule that fired, with the conditions that trigger it and remediation where one exists. Open the interactive report for evidence lines and context.

About Skillgate

Skillgate is a free scanner from Mitiga Labs for AI agent skills, hooks, MCP configs, and instruction files (SKILL.md, CLAUDE.md, AGENTS.md, .cursorrules, .claude/settings.json). It runs static rules plus an LLM judge and maps each finding to a known attack technique. Static analysis only: it never executes the file it scans. No scanner is 100% accurate - a verdict is a signal, not a guarantee. Browse all detection rules.