linktree-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements standard analytics functionality, pulling data such as click counts, views, and audience demographics from the Linktree platform. The external references are to official Linktree developer documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data including link titles and referrer strings from the Linktree API, which represents a potential surface for indirect prompt injection if those strings contain malicious instructions.
  • Ingestion points: Link titles, location names, and referrer sources are ingested via the Linktree SDK analytics methods defined in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill is configured with access to Read, Write, Edit, Bash, and Grep tools.
  • Sanitization: The provided logic logs fetched data directly to the console without explicit sanitization or validation of the remote strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:51 AM
Security Audit — agent-trust-hub — linktree-core-workflow-b