Back to skill

Security audit

restaurant-review-responder

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious with medium confidence: one scanner found a permissions-scope concern, and another flagged a possible tool reference, while coverage is incomplete because some referenced paths were missing.

Consider the suspicious verdict and medium confidence before installing. The scan covered all four listed components but was marked partial because several referenced paths were missing, so the evidence is incomplete. Check the skill's file-writing needs and the runtime permissions it would receive; the scan does not confirm those controls.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

YARA rule 'offensive_tool_references': References to well-known offensive security tools [hacktools]

High
Category
YARA Match
Confidence
70% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/tally_review_themes.py (reported line 41)May include surrounding context.

python
",
      "server",
      "staff"
    ],
    "food quality": [
      "cold",
      "dry",
      "bland",
      "undercooked",
      "burnt"
    ],
    "billing": [
      "overcharged",
      "bill",
      "charge",
      "tip",
      "cashier"
    ],
    "cleanliness": [
      "dirty",
      "sticky",
      "restroom",
      "flies",
      "crumbs"
    ]
  }
}

Usage:
    python3 restaurant_review_responder.py --input <file> --out <dir>
"""

import argparse
import os
import re
import sys

TITLE = "Restaurant Review Responder"


def read_flat(path):
    """Read a small YAML-ish file: `key: value`, `- item` lists, '#' comments."""
    data, key = {}, None
    try:
        raw = open(path, encoding="utf-8", errors="replace").read()
    except OSError as exc:
        raise SystemExit(f"cannot read {path}: {exc}")
    for line in raw.splitlines():
        if not line.strip() or line.strip().startswith("#"):
            continue
        stripped = line.strip()
        if stripped.startswith("

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.