Risky: claudeos - CLAUDE.md | Skillgate

Skillgate scanned agents/android-tester/CLAUDE.md in claudeos and rated it Risky with a risk score of 37/100 (6 detections).

Skillgate found low-to-medium risk patterns that are common in legitimate files but worth a look before you trust the file.

What was found

• SG-028 File Exfiltration - HIGH: Bulk file reads, credential file access, data staging via tar/zip/rsync/S3 upload
• SG-087 External binary/archive payload reference - MEDIUM (2x): Instruction in a markdown/agent-config file routes the agent to extract or execute content from a binary/archive sibling whose contents are not visible to this scan. Indirection itself is signal; manual review of the referenced file is advised.
• SG-037 Cleartext Secrets in Config - LOW: Cleartext secrets in env / config files
• SG-092 Command-file exfiltration shape - LOW (2x): Instruction file (slash-command, sub-agent, hook, skill, or CLAUDE.md / .cursorrules) co-occurs an external HTTP egress verb, a hardcoded destination identifier, and an env-secret materialization within a single block. Severity is raised to HIGH when the file path is `.claude/commands/`, `.claude/agents/`, or the .codex/ equivalents - those paths are auto-trusted on user invocation.

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.