skill-install
Install Claude skills from GitHub repositories with automated security scanning. Triggers when users want to install skills from a GitHub URL, need to browse available skills in a repository, or want to safely add new skills to their Claude environment.
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill fetches and stores raw repository file contents and then writes those files back (using the Write tool), so the LLM must handle and output file contents verbatim — which can include API keys, tokens, or other secrets found in the repo or files.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Outsider-authored free text from a user-supplied GitHub repository (public web content) is fetched at runtime via WebFetch and raw GitHub content URLs, then inserted into the LLM prompt as `{skill_content}` during the security scan template application.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill runtime fetches remote skill files (including the security scan prompt) via raw GitHub URLs—e.g. https://raw.githubusercontent.com/{owner}/{repo}/{branch}/skills/{skill_name}/{file_path}—and then loads the fetched references/security_scan_prompt.md to control the agent's analysis prompts, so remote content directly controls agent instructions.
- Repository
- stellarlinkco/myclaude
- Commit
f2e75c1
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.