skill-installer
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The install/list scripts fetch repository archives and GitHub API content at runtime (e.g., "https://codeload.github.com/{owner}/{repo}/zip/{ref}" and "https://api.github.com/repos/{repo}/contents/{path}?ref={ref}"), which are then installed as skills (requiring SKILL.md) and thus can directly control agent prompts/instructions; these remote URLs are used during runtime to obtain that content.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly instructs the agent to "request escalation" for running networked installation scripts (encouraging obtaining elevated privileges) and even allows overwriting preinstalled .system skills, which could lead to modifying the host state.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata