Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/webflow-install-auth/Gen Agent Trust Hub

webflow-install-auth

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Webflow API, creating a surface for potential indirect prompt injection attacks. 1. Ingestion points: The skill reads site information (names, IDs, short names) via webflow.sites.list() in SKILL.md. 2. Boundary markers: Absent. There are no markers to delimit external data from instructions or warnings to the agent to ignore instructions within that data. 3. Capability inventory: The skill uses npm, pnpm, and yarn for package management (via allowed-tools in SKILL.md) and performs file write operations for .env configuration in SKILL.md. 4. Sanitization: Absent. External site data is processed and logged without explicit validation or sanitization.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the official webflow-api library from the npm registry, which is the official SDK for a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:54 AM