Back to skill

Security audit

sum_and_translate_install_check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed environment checker and optional installer for a PDF summarization and translation pipeline, with no evidence of hidden exfiltration, persistence, or destructive behavior.

Install this only if you want it to modify the active Python environment for a PDF OCR/summarization/translation workflow. Prefer running it in a virtual environment because --install downloads many packages and Chromium, and be aware that the import check calls python-dotenv, which may load a local .env file into the script process.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

exec() call detected

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

Direct exec() call allows arbitrary code execution. An attacker can inject code that runs with the full privileges of the process.

Content

Scanner excerpt · install_libraries.py (reported line 116)May include surrounding context.

python
failed = []
    for label, code in CHECKS:
        try:
            exec(code, {})
        except Exception as exc:
            print(f"FAIL {label}: {type(exc).__name__}: {exc}", flush=True)
            failed.append(label)

exec() call detected

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

Direct exec() call allows arbitrary code execution. An attacker can inject code that runs with the full privileges of the process.

Content

Scanner excerpt · install_libraries.py (reported line 125)May include surrounding context.

python
failed = []
    for label, code in CHECKS:
        try:
            exec(code, {})
        except Exception as exc:
            print(f"FAIL {label}: {type(exc).__name__}: {exc}", flush=True)
            failed.append(label)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill is an executable script that can inspect the environment and perform package installation, but the metadata declares no explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can allow broader shell/environment access than reviewers or orchestrators expect, increasing the risk of unintended command execution or dependency changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and usage conditions are written entirely in Russian and implicitly prescribe Russian as the operating language. The policy specifically calls for flagging language or locale constraints when the skill does not offer the user a language/locale choice or clearly justify the restriction.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This is a code file, so SQP-3 applies to natural-language content in docstrings and strings. The file presents instructions and operational output in Russian only, and there is no indication that the skill is region-specific or that users can opt into another language, which violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · install_libraries.py (reported line 83)May include surrounding context.

python
def run(cmd, what):
    """Запустить подпроцесс, вернуть True/False и напечатать понятный итог."""
    try:
        proc = subprocess.run(cmd)
    except (OSError, subprocess.SubprocessError) as exc:
        print(f"FAIL {what}: не удалось запустить — {exc}", flush=True)
        return False