Interceptor

Fail

Audited by Snyk on Aug 15, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). The GitHub repo linked (https://github.com/Hacker-Valley-Media/Interceptor) is referenced as the upstream source for signed .pkg installers and builds — GitHub releases from an unfamiliar/non-official publisher that distribute .pkg installers are a supply-chain / executable-download risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). The skill intentionally exposes powerful local automation and surveillance surfaces (an unauthenticated UNIX socket that inherits TCC privileges, cross-app recording including clipboard/files/network, AppleEvents dispatched silently, persistent network overrides) and also mandates a hidden local HTTP/notify call — together these are high-risk, abuse-capable patterns that look like deliberate backdoor/telemetry vectors.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). In the Interceptor skill’s required runtime workflow, the agent reads outsider-authored free text at runtime via the monitor/recording pipeline: interceptor monitor export <sid> --plan and related monitor outputs include human-provided instruction strings and recorded event bodies that are then parsed/executed in ReplayFlow.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill contains an Update workflow that at runtime pulls/builds from the upstream repository https://github.com/Hacker-Valley-Media/Interceptor (git fetch/pull + build/install), which fetches remote code that is then built/executed on the host.

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

  • Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill repeatedly instructs installing system components, modifying binaries and native-messaging manifests, registering LaunchAgents, writing to /usr/local and /opt/homebrew, and running codesign/launchctl/install scripts — actions that change system state and can require elevated privileges or otherwise alter the host.

Issues (5)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

E006
CRITICAL

Malicious code pattern detected in skill scripts.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

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
Aug 15, 2026, 06:48 PM
Issues
5
Security Audit — snyk — Interceptor