Scanned repository says: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills.
Inspect GitHub sourceVotes show community interest, not safety. They never change this score.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills.
README.md:3License: Apache 2.0
README.md:6SkillSpector helps you answer: "Is this skill safe to install?"
README.md:12Multi-format input: Scan Git repos, URLs, zip files, directories, or single files
README.md:26Two-stage analysis: Fast static analysis + optional LLM semantic evaluation
README.md:28Live vulnerability lookups: SC4 queries OSV.dev for real-time CVE data with automatic offline fallback
README.md:29Open-source software notice: This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.
README.md:38Manifest declares Python >=3.12,<3.15 as a requirement.
pyproject.toml:11Declares a dependency on typer.
pyproject.toml:34All make targets assume a virtual environment is already created and activated. The Makefile uses uv if available, else pip.
README.md:883Declares a dependency on rich.
pyproject.toml:35Declares a dependency on httpx.
pyproject.toml:36Declares a dependency on pywhatwgurl.
pyproject.toml:37Declares a dependency on regex.
pyproject.toml:38Declares a dependency on packaging.
pyproject.toml:39Non-English content: May miss patterns in other languages
README.md:959A license or copying file is present; its terms have not been reviewed.
LICENSE:1Image-based attacks: Cannot analyze text in images
README.md:960Encrypted/binary code: Cannot analyze compiled or encrypted content
README.md:961These are references in selected source files, not proof that a feature works at runtime.
Observed in the scanned archive at Oct 9, 2026, 8:20 AM UTC. Archive digest sha256:cf5dff912b7b43a0…. Source links open current GitHub HEAD and may differ from the scan. Repository statements are unreviewed and do not affect the score.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
Share the full report so its scope and limits travel with the score.
