fix(skills): detect prompt injection patterns and block cache file reads

Adds two security layers to prevent prompt injection via skills hub
cache files (#1558):

1. read_file: blocks direct reads of ~/.hermes/skills/.hub/ directory
   (index-cache, catalog files). The 3.5MB clawhub_catalog_v1.json
   was the original injection vector — untrusted skill descriptions
   in the catalog contained adversarial text that the model executed.

2. skill_view: warns when skills are loaded from outside the trusted
   ~/.hermes/skills/ directory, and detects common injection patterns
   in skill content ("ignore previous instructions", "<system>", etc.).

Cherry-picked from PR #1562 by ygd58.

tools/file_tools.py

@@ -169,6 +169,27 @@ def clear_file_ops_cache(task_id: str = None):
 def read_file_tool(path: str, offset: int = 1, limit: int = 500, task_id: str = "default") -> str:
     """Read a file with pagination and line numbers."""
     try:
+        # Security: block direct reads of internal Hermes cache/index files
+        # to prevent prompt injection via catalog or hub metadata files.
+        import pathlib as _pathlib
+        _resolved = _pathlib.Path(path).expanduser().resolve()
+        _hermes_home = _pathlib.Path("~/.hermes").expanduser().resolve()
+        _blocked_dirs = [
+            _hermes_home / "skills" / ".hub" / "index-cache",
+            _hermes_home / "skills" / ".hub",
+        ]
+        for _blocked in _blocked_dirs:
+            try:
+                _resolved.relative_to(_blocked)
+                return json.dumps({
+                    "error": (
+                        f"Access denied: {path} is an internal Hermes cache file "
+                        "and cannot be read directly to prevent prompt injection. "
+                        "Use the skills_list or skill_view tools instead."
+                    )
+                })
+            except ValueError:
+                pass
         file_ops = _get_file_ops(task_id)
         result = file_ops.read_file(path, offset, limit)
         if result.content:

tools/skills_tool.py

@@ -873,6 +873,37 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
                 ensure_ascii=False,
             )
 
+        # Security: warn if skill is loaded from outside the trusted skills directory
+        try:
+            skill_md.resolve().relative_to(SKILLS_DIR.resolve())
+            _outside_skills_dir = False
+        except ValueError:
+            _outside_skills_dir = True
+
+        # Security: detect common prompt injection patterns
+        _INJECTION_PATTERNS = [
+            "ignore previous instructions",
+            "ignore all previous",
+            "you are now",
+            "disregard your",
+            "forget your instructions",
+            "new instructions:",
+            "system prompt:",
+            "<system>",
+            "]]>",
+        ]
+        _content_lower = content.lower()
+        _injection_detected = any(p in _content_lower for p in _INJECTION_PATTERNS)
+
+        if _outside_skills_dir or _injection_detected:
+            _warnings = []
+            if _outside_skills_dir:
+                _warnings.append(f"skill file is outside the trusted skills directory (~/.hermes/skills/): {skill_md}")
+            if _injection_detected:
+                _warnings.append("skill content contains patterns that may indicate prompt injection")
+            import logging as _logging
+            _logging.getLogger(__name__).warning("Skill security warning for '%s': %s", name, "; ".join(_warnings))
+
         parsed_frontmatter: Dict[str, Any] = {}
         try:
             parsed_frontmatter, _ = _parse_frontmatter(content)