Trust Assessment
screenshot 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 17 findings: 6 critical, 9 high, 1 medium, and 1 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Dangerous call: subprocess.check_output().
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings17
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:110 | |
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:193 | |
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:207 | |
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:237 | |
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:247 | |
| 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 | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:401 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'ensure_macos_permissions'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:237 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'activate_app'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:247 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'mac_default_dir'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:110 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:193 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'swift_json'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:207 | |
| HIGH | Dangerous call: subprocess.check_output() Call to 'subprocess.check_output()' detected in function 'capture_linux'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/media/screenshot/scripts/take_screenshot.py:401 | |
| HIGH | Arbitrary File Write via User-Controlled Path (Python) The `take_screenshot.py` script allows users to specify an arbitrary output path for screenshots via the `--path` argument. The script then creates parent directories for this path using `path.parent.mkdir(parents=True, exist_ok=True)`. While path normalization (`expanduser()`) is applied, it does not restrict the base directory where files can be written. This enables writing files to almost any location on the filesystem where the executing user has write permissions, including sensitive system directories. An attacker could use this to overwrite or create files in critical system locations (e.g., `/etc/cron.d/malicious_job`), potentially leading to system compromise, data corruption, or denial of service. Restrict the output path to a predefined, secure directory (e.g., a sandbox output directory, or a user's designated 'Screenshots' folder) and prevent writing to arbitrary system paths. If user-specified paths are necessary, implement strict validation to ensure they are within an allowed, non-sensitive subtree, or require explicit user confirmation for writes outside a default safe location. | Static | scripts/take_screenshot.py:127 | |
| HIGH | Arbitrary File Write via User-Controlled Path (PowerShell) The `take_screenshot.ps1` script allows users to specify an arbitrary output path for screenshots via the `-Path` parameter. The script then creates parent directories for this path using `New-Item -ItemType Directory -Path $parent -Force`. While path normalization (`[System.IO.Path]::GetFullPath()`) is applied, it does not restrict the base directory where files can be written. This enables writing files to almost any location on the filesystem where the executing user has write permissions, including sensitive system directories. An attacker could use this to overwrite or create files in critical system locations (e.g., `C:\Windows\System32\malicious.dll`), potentially leading to system compromise, data corruption, or denial of service. Restrict the output path to a predefined, secure directory (e.g., a sandbox output directory, or a user's designated 'Screenshots' folder) and prevent writing to arbitrary system paths. If user-specified paths are necessary, implement strict validation to ensure they are within an allowed, non-sensitive subtree, or require explicit user confirmation for writes outside a default safe location. | Static | scripts/take_screenshot.ps1:70 | |
| HIGH | LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 6 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion. | LLM | (sanity check) | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/6d5b80c1f6a99ff0)
Powered by SkillShield