Trust Assessment
tencent-cos 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 11 findings: 4 critical, 6 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.Popen(), Dangerous call: subprocess.run().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings11
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | skills/shawnminh/tencentcloud-cos-skills/scripts/cos_wrapper.py:109 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:62 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:73 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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 | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:253 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function 'start_mcp_server'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/shawnminh/tencentcloud-cos-skills/scripts/cos_wrapper.py:109 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'check_dependencies'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:62 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'check_dependencies'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:73 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_example'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/shawnminh/tencentcloud-cos-skills/test_skill.py:253 | |
| HIGH | Unpinned Dependency in Installation Script The installation script `install.sh` and the `SKILL.md` documentation instruct users to install the `cos-mcp` package using `npm install -g cos-mcp@latest`. Relying on `@latest` for a global dependency introduces a supply chain risk. If a malicious update to `cos-mcp` is published, it could be automatically installed, potentially compromising the system or exfiltrating credentials. It is best practice to pin dependencies to a specific version or a version range to ensure reproducibility and security. Pin the `cos-mcp` dependency to a specific major or minor version (e.g., `cos-mcp@^1.2.3` or `cos-mcp@1.2.3`) instead of `@latest`. Regularly review and update the pinned version to incorporate security fixes. | LLM | install.sh:89 | |
| HIGH | Unpinned Dependency in Skill Documentation The `SKILL.md` documentation, which guides users on installing the skill, specifies `npm install -g cos-mcp@latest`. This practice of using `@latest` for a critical dependency creates a supply chain vulnerability. An attacker could introduce malicious code into a new 'latest' version of `cos-mcp`, which would then be automatically installed by users following the documentation, leading to potential system compromise or data exfiltration. Update the `SKILL.md` to instruct users to install `cos-mcp` with a specific version or a version range (e.g., `npm install -g cos-mcp@^1.2.3` or `npm install -g cos-mcp@1.2.3`). This ensures that installations are deterministic and less susceptible to unexpected or malicious changes in future package versions. | LLM | SKILL.md:49 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/shawnminh/tencentcloud-cos-skills/install.sh:153 |
Scan History
Embed Code
[](https://skillshield.io/report/528f4f6460cb3c8c)
Powered by SkillShield