Trust Assessment
gpt-image-1-5 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 18 findings: 8 critical, 10 high, 0 medium, and 0 low severity. Key findings include Unsafe environment variable passthrough, File read + network send exfiltration, Credential harvesting.
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 June 1, 2026 (commit 9b0e00ad). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings18
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:15 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:20 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:25 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:121 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:126 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:131 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/gpt-image-1-5/SKILL.md:136 | |
| CRITICAL | Credential harvesting Reading well-known credential environment variables Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/gpt-image-1-5/scripts/generate_image.py:35 | |
| HIGH | Unsafe environment variable passthrough Access to well-known credential environment variables Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/gpt-image-1-5/scripts/generate_image.py:35 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:15 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:20 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:25 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:121 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:126 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:131 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/gpt-image-1-5/SKILL.md:136 | |
| HIGH | Arbitrary File Read via Path Traversal in Input Parameters The script allows reading arbitrary files from the filesystem by not properly validating or sanitizing the `--input-image` and `--mask` parameters. An attacker can use path traversal sequences (e.g., `../../../etc/passwd`) to read sensitive files outside the intended directories. Before opening or checking existence of `args.input_image` and `args.mask`, sanitize the paths to prevent path traversal. This can be done by resolving the path and ensuring it is within an allowed base directory, or by extracting only the filename component and joining it with a secure, designated input directory. For example, `Path(safe_input_dir) / Path(args.input_image).name`. | LLM | scripts/generate_image.py:189 | |
| HIGH | Arbitrary File Write via Path Traversal in Output Filename The script allows writing files to arbitrary locations on the filesystem by not properly validating or sanitizing the `--filename` parameter. An attacker can use path traversal sequences (e.g., `../../../tmp/malicious.png`) to write files outside the intended output directory, potentially overwriting critical system files or placing malicious content in unexpected locations. Before writing to `output_path`, sanitize the `args.filename` to prevent path traversal. This can be done by resolving the path and ensuring it is within an allowed base output directory, or by extracting only the filename component and joining it with a secure, designated output directory. For example, `output_path = Path(safe_output_dir) / Path(args.filename).name`. | LLM | scripts/generate_image.py:180 |
Scan History
Embed Code
[](https://skillshield.io/report/5ab5b8ffdb461fb3)
Powered by SkillShield