Back to skill

Security audit

Slogan Maker

Security checks for vulnerabilities and agentic risk

Overview

The skill includes a normal slogan generator, but it also ships an unrelated data-tool command that creates local storage and logs user arguments without clear disclosure.

Review before installing. The slogan generator itself is local and purpose-aligned, but the package also includes an unrelated data-processing command that writes local history. Avoid entering sensitive campaign text, customer identifiers, file paths, or private queries unless the publisher removes or clearly documents that script and its logging behavior.

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 Persistent Plaintext Logging of User-Supplied Arguments

Content
View full analysis
> "$DATA_DIR/history.log"; } cmd_query() { echo " Query: $*" _log "query" "${1:-}" } cmd_import() { echo " Importing: $1" _log "import" "${1:-}" } cmd_export() { echo " Exporting to: ${1:-stdout}" _log "export" "${1:-}" } cmd_transform() { echo " Transforming: $1 -> $2" _log "transform" "${1:-}" } cmd_validate() { echo " Validating schema..." _log "validate" "${1:-}" } cmd_stats() { echo " Records: $(wc -l < "$DB" 2>/dev/null || echo 0)" _log "stats" "${1:-}" } cmd_schema() { echo " Fields: id, name, value, timestamp" _log "schema" "${1:-}" } cmd_sample() { [ -f "$DB" ] && head -5 "$DB" || echo "No data" _log "sample" "${1:-}" } cmd_clean() { echo " Cleaning data..." _log "clean" "${1:-}" } cmd_dashboard() { echo " Total: $(wc -l < "$DB" 2>/dev/null || echo 0) records" _log "dashboard" "${1:-}" } ``` ### Technical Analysis The script creates a persistent data directory and appends the first argument supplied to multiple commands to `history.log` in plaintext. This logging is automatic, is not disclosed in `SKILL.md`, and is unrelated to the declared slogan-generation functionality. Arguments passed to commands such as `query`, `import`, `export`, and `transform` may contain confidential search terms, campaign content, customer information, internal file paths, or other sensitive data. The log has no redaction, encryption, retention limit, consent mechanism, or explicit restrictive permission setup. The directory and file permissions dep ...[truncated 2075 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 presents a marketing copy/slogan generation skill, but the code implements a generic data processing CLI. Its help text explicitly says 'Data processing and analysis toolkit,' and the commands operate on local data files/logs rather than generating slogans or performing translation/rhyming. This is a materially different primary purpose, with undeclared capabilities around data handling and filesystem logging. Therefore the description does not accurately represent the code's actual behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The script presents itself as a generic data-processing toolkit with commands like import, export, query, transform, and dashboard, which materially conflicts with the declared skill purpose of slogan generation. This kind of capability/purpose mismatch is dangerous because it can conceal undeclared functionality, mislead reviewers and users about what the skill actually does, and create a path for data access or collection under a benign-seeming manifest.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The inline description and help output explicitly advertise a 'Data processing and analysis toolkit' instead of a slogan maker, directly misrepresenting the skill's intended function. Misrepresentation increases security risk because it undermines trust boundaries, impairs review, and may hide unauthorized data handling behind misleading metadata.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This shell script’s natural-language interface and help output are predominantly in Chinese, including command descriptions, prompts, and examples, while presenting itself generically as a slogan maker rather than a clearly region-specific tool. Under the policy rule, forcing a specific language without user opt-in is a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The phrase "完全适配中文用户习惯" is a natural-language locale preference that presents the skill as tailored to Chinese users only. Because the file does not also offer user language/locale choice or explain a justified region-specific constraint, this can be read as a locale policy violation under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all substantive guidance in Chinese, which imposes a specific language on users without any visible opt-in or explanation. The stated policy calls for flagging language or locale constraints unless the skill offers a choice or clearly documents a justified regional limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.