restaurant-review-responder

• Outcome: Pass
• Latest audit: Oct 22, 2026 · 7:28 PM UTC
• Version: 1.0.6

Overview

The bundled skill drafts restaurant review replies and produces a local theme report, with a separate Windows app clearly marked as optional.

Keep input logs and reports private because reports include review excerpts, and review drafts before sending them. The local workflow does not require the optional Windows app; assess that unsigned download separately, since this verdict does not establish its safety.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive 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.

Static analysis

No suspicious patterns detected.