my-computer
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow's browser pipeline (
browser_pipeline/mycomputer browse) navigates to arbitrary URLs and extracts DOM text, so outsider-authored web page content is read only after the agent selects or fetches a page, which makes this low rather than medium.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs setup to pipe a remote
install.shfrom the individually owned GitHub repo1broseidon/mcintobash, and that content is executed, so it is an operational dependency; the publisher is an individual project owner (unofficial, not strong first-party provenance) with no weak-tier warning signs such as disabled checks, raw IPs, or obfuscation, which makes it common/reputable unofficial and therefore medium.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill mainly teaches GUI automation, but it tells the agent to auto-install a binary via a curl-piped-to-bash script and documents a sudo-requiring system-wide install option, though it also offers an inspect-first variant and defaults to a no-sudo user install.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata