dissect-competitor-app

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is entirely composed of markdown instructions for a manual teardown protocol and contains no executable code.\n- [EXTERNAL_DOWNLOADS]: The skill mentions established services and platforms (App Store, Figma, Loom, and QuickTime) for manual documentation purposes. These are recognized as well-known, trusted services.\n- [PROMPT_INJECTION]: The skill defines a process for ingesting external application content.\n
  • Ingestion points: Phase 2 and Phase 3 (documentation of competitor app onboarding and core flows).\n
  • Boundary markers: Absent.\n
  • Capability inventory: None (no tools or automated actions are requested in the skill configuration).\n
  • Sanitization: Absent.\n
  • Assessment: While the skill documents an ingestion surface for untrusted external data, the lack of automated tool execution prevents any exploitation of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 11:17 PM
Security Audit — agent-trust-hub — dissect-competitor-app