Back to skill

Security audit

Meme Coin Scanner

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly acts like a meme-coin lookup tool, but it overstates its automated safety checks and includes an unrelated local security utility that can persistently log sensitive inputs.

Review this skill before installing. Do not rely on it as a definitive honeypot, holder concentration, or rug-pull detector, and do not enter secrets into the bundled script.sh hash, encrypt, or password commands. Expect token addresses and listing queries to be sent to DexScreener when using the lookup features.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/script.sh:35
Finding

Plaintext Persistence of Potentially Sensitive Command Arguments

Content
View full analysis
> "$DATA_DIR/history.log"; } ``` ```bash cmd_encrypt() { echo " Encrypting: $1" _log "encrypt" "${1:-}" } cmd_hash() { echo "$1" | sha256sum | cut -d" " -f1 _log "hash" "${1:-}" } ``` ### Technical Analysis The `_log` function appends the complete second argument to a persistent `history.log` file. Both `cmd_encrypt` and `cmd_hash` pass their original user-supplied values to this function without redaction. Users may reasonably supply passwords, API tokens, recovery codes, or other confidential values to commands advertised as encryption and hashing utilities. Although `cmd_hash` prints a SHA-256 digest, it separately records the unhashed input. The `encrypt` command does not perform encryption and likewise records the plaintext value. The script does not establish a restrictive `umask` or explicitly create the log with mode `0600`. Consequently, its effective permissions depend on the invoking environment. The behavior is also unrelated to the meme-coin scanning functionality declared in `SKILL.md`, so it exceeds the data retention necessary for the Skill's stated purpose. ### Attack Path 1. A user invokes `scripts/script.sh encrypt ` or `scripts/script.sh hash `. 2. The command forwards the raw value to `_log`. 3. `_log` appends the raw value to the persistent data file at `$DATA_DIR/history.log`. 4. A local user, process, backup reader, or later attacker with access to that file retrieves the plaintext secret. 5. The exposed value may then be reused against the service or account for which it was intended. This path requires local read access to the resulting history file or to a copy of it; the reviewed code does not transmit the log over the network. ### Impact ...[truncated 455 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/script.sh:72
Finding

Security Password Generator Uses a Non-Cryptographic PRNG

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (11)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill claims automated honeypot detection, liquidity analysis, and holder concentration analysis, but the finding indicates it only provides links or checklist guidance and does not perform the stated checks. This is dangerous because users may rely on the skill's output as a security signal for financial decisions, creating a false sense of safety around scam tokens.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill claims automated honeypot detection, liquidity analysis, and holder concentration analysis, but the finding indicates it only provides links or checklist guidance and does not perform the stated checks. This is dangerous because users may rely on the skill's output as a security signal for financial decisions, creating a false sense of safety around scam tokens.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The implemented behavior materially contradicts the advertised skill purpose: instead of analyzing meme-coin risks, the script presents a generic security toolkit with unrelated capabilities. This kind of functionality mismatch is dangerous because it can conceal unauthorized data handling or repurpose user trust to run tooling outside the expected scope, increasing the likelihood of deceptive or Trojanized behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The skill advertises commands that inherently require external network access to scan tokens, fetch new listings, and show trending coins, but the manifest does not declare any tool scope or allowed network capability. Missing capability declarations weaken reviewability and can let networked behavior occur without clear user or platform visibility, which is a real security governance issue even if the visible markdown itself is not executable.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/meme.sh (reported line 39)May include surrounding context.

sh
# Try DexScreener for basic info
try:
    url = "https://api.dexscreener.com/latest/dex/tokens/{}".format(token)
    req = Request(url)
    req.add_header("User-Agent", "MemeCoinScanner/1.0")
    resp = urlopen(req, timeout=15)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/meme.sh (reported line 174)May include surrounding context.

sh
# Try DexScreener for basic info
try:
    url = "https://api.dexscreener.com/latest/dex/tokens/{}".format(token)
    req = Request(url)
    req.add_header("User-Agent", "MemeCoinScanner/1.0")
    resp = urlopen(req, timeout=15)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/meme.sh (reported line 280)May include surrounding context.

sh
# Try DexScreener for basic info
try:
    url = "https://api.dexscreener.com/latest/dex/tokens/{}".format(token)
    req = Request(url)
    req.add_header("User-Agent", "MemeCoinScanner/1.0")
    resp = urlopen(req, timeout=15)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The inline help and comments explicitly describe the script as a security scanning and hardening tool, which directly conflicts with the skill metadata claiming meme-coin analysis. Such misrepresentation is a supply-chain red flag because users may invoke the skill under false assumptions, allowing unrelated actions and persistence to occur under a trusted label.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The logging helper persistently records command usage and arguments to a history file without disclosure, which can capture sensitive user inputs over time. In this script, commands like check, encrypt, and hash echo or log user-supplied arguments, so secrets, token symbols, wallet identifiers, or other sensitive data may be stored locally without consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Encryption, hashing, and password-generation functions are outside the expected scope of a meme-coin scanner and expand the attack surface without clear justification. In a mislabeled skill, these capabilities are especially suspicious because they can facilitate credential handling or covert utility behavior that users did not request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Printing a generated password directly to the terminal can expose it via shell history capture, terminal scrollback, screen recording, shoulder surfing, or logging by surrounding systems. While not always exploitable on its own, the lack of warning or safer handling increases the chance of accidental credential disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.