Back to skill

Security audit

Math Solver

Security checks for vulnerabilities and agentic risk

Overview

The advertised math helper includes a separate generic local data utility that stores user-supplied text on disk, which is not disclosed by the skill's stated purpose.

Review this skill before installing. The math prompt script is mostly consistent with the advertised purpose, but the package also ships an unrelated local storage CLI that can retain text you pass to it. Avoid entering private or sensitive data unless the publisher removes or clearly documents that storage behavior and provides user control over retention and deletion.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/script.sh:5
Finding

Undisclosed Plaintext Persistence of User-Supplied Arguments

Content
View full analysis
[args] Commands: run Execute main function config Configuration status Show status init Initialize list List items add Add entry remove Remove entry search Search export Export data info Show info help Show this help version Show version Data: \$DATA_DIR EOF } _log() { echo "$(date '+%m-%d %H:%M') $1: $2" >> "$DATA_DIR/history.log"; } cmd_run() { echo " Running: $1" _log "run" "${1:-}" } cmd_config() { echo " Config: $DATA_DIR/config.json" _log "config" "${1:-}" } cmd_status() { echo " Status: ready" _log "status" "${1:-}" } cmd_init() { echo " Initialized in $DATA_DIR" _log "init" "${1:-}" } cmd_list() { [ -f "$DB" ] && cat "$DB" || echo " (empty)" _log "list" "${1:-}" } cmd_add() { echo "$(date +%Y-%m-%d) $*" >> "$DB"; echo " Added: $*" _log "add" "${1:-}" } cmd_remove() { echo " Removed: $1" _log "remove" "${1:-}" } cmd_search() { grep -i "$1" "$DB" 2>/dev/null || echo " Not found: $1" _log "search" "${1:-}" } cmd_export() { [ -f "$DB" ] && cat "$DB" || echo "No data" _log "export" "${1:-}" } ``` ### Technical Analysis The script creates a persistent data directory on every invocation and writes command arguments to plaintext files: - `_log` appends the first supplied argument to `history.log`. - `cmd_add` ap ...[truncated 2430 chars]
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description says this skill is a mathematics analysis and learning tool with solver, graphing, formula reference, unit conversion, and practice generation features. The supplied shell script instead implements a generic local CLI utility that stores entries in files under a data directory, supports add/list/search/export-style operations, and logs usage history. There is no code for parsing or solving math problems, rendering graphs, converting units, referencing formulas, or generating exercises. The primary purpose and exposed capabilities are materially different from the declaration, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The script's implemented behavior is a generic local notes/data utility, not a math-solving tool as declared in the manifest. This capability mismatch is dangerous because it can mislead users and reviewers about what the skill actually does, increasing the risk of unauthorized data collection, storage, or later abuse under an unrelated trusted description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and description present the skill as a Chinese-language learning tool ('数学题解析与学习工具') and the document content is primarily in Chinese, but there is no statement that users may choose their preferred language. This can violate language/locale policy when a skill implicitly enforces one language without explicit opt-in or a documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The practice command defines grade levels, topics, prompts, and usage examples only in Chinese, and the help output mixes Chinese command descriptions without indicating that another language is supported. This creates a locale/language constraint in the skill's natural-language interface without explicit user opt-in or a documented justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The in-code description labels the tool as a 'Multi-purpose utility tool,' which contradicts the manifest's math-focused description. This inconsistency is a supply-chain and trust signal issue: it suggests the published identity of the skill does not match the shipped code, making hidden or unauthorized functionality harder to detect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese-language instructions and descriptions throughout, but it does not indicate that the skill is Chinese-only or provide any user opt-in for language preference. That can conflict with language/locale policy requirements when users are not explicitly given a choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.