autosync-ic-skills

Fail

Audited by Snyk on Nov 19, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill openly installs a SessionStart hook that silently and automatically replaces the user's project skills with whatever the remote index publishes on each session, without per-update review, which is a risky unrequested change to the user's work rather than clear malicious intent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The skill has an inbound dependency: it fetches the sync script, a discovery index, and skill files from skills.internetcomputer.org during setup and on every session, and Claude adopts those skills as instructions. The domain is the official Internet Computer domain, but no signature or digest is enforced, so provenance falls to unverified first-party, which is medium.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill persuades the agent to add a persistent SessionStart hook that fetches and runs a remote script on every session, and to suggest sudo package installs, though it stays within project-local config, asks before installing, and does not bypass trust prompts.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 19, 2026, 10:59 AM
Issues
3