Security Audit
dkyazzentwatwa/chatgpt-skills:code-profiler
github.com/dkyazzentwatwa/chatgpt-skillsTrust Assessment
dkyazzentwatwa/chatgpt-skills:code-profiler received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 5 critical, 1 high, 1 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, Dangerous call: compile().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on February 24, 2026 (commit d4bad335). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | code-profiler/scripts/code_profiler.py:16 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | code-profiler/scripts/code_profiler.py:38 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | code-profiler/scripts/code_profiler.py:39 | |
| CRITICAL | Dangerous call: exec() Call to 'exec()' detected in function 'profile_script'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | code-profiler/scripts/code_profiler.py:39 | |
| CRITICAL | Arbitrary Code Execution via `exec()` on User-Provided Script The `profile_script` method in `code_profiler.py` reads and executes the content of an arbitrary Python script specified by the user. This allows an attacker to execute any Python code with the permissions of the agent, leading to full system compromise, data exfiltration, or denial of service. Avoid executing arbitrary user-provided code. If profiling user code is necessary, consider using a secure sandboxing mechanism (e.g., a containerized environment) or restrict the execution to predefined, safe code snippets. Do not allow the agent to directly execute external files provided by untrusted input. | Static | scripts/code_profiler.py:34 | |
| HIGH | Arbitrary File Write via User-Controlled Output Path The `export_report` method allows writing the profiling report to an arbitrary file path specified by the user through the `--output` argument. An attacker could use this to overwrite sensitive system files (e.g., `/etc/passwd`, configuration files) or write data to locations that could aid in further exploitation or data exfiltration. Restrict the output path for reports to a designated, non-sensitive directory within the agent's workspace (e.g., a temporary directory or a specific output folder). Implement path sanitization and validation to prevent directory traversal attacks and ensure files are only written to approved locations. | Static | scripts/code_profiler.py:61 | |
| MEDIUM | Dangerous call: compile() Call to 'compile()' detected in function 'profile_script'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | code-profiler/scripts/code_profiler.py:38 |
Scan History
Embed Code
[](https://skillshield.io/report/388edee3ad0504b6)
Powered by SkillShield