claude-code-config: Skill for Claude Code

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

• high Prompt Injection · line 81
  Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
  Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
• high Data Exfiltration · line 101
  Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
  Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
• high Data Exfiltration · line 169
  Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
  Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
• high Data Exfiltration · line 570
  Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
  Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
• high Data Exfiltration · line 584
  Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
  Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
• high Prompt Injection · line 179
  Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
  Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
• high Privilege Escalation · line 592
  Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
  Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
• medium Excessive Agency · line 3
  Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
  Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
• medium Excessive Agency · line 593
  Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
  Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
• medium Excessive Agency · line 736
  Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
  Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
• medium Excessive Agency · line 748
  Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
  Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.