linkedin-craft

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill references a legitimate external website (jaymountconsulting.com) for educational course content.
  • [SAFE]: The skill uses a parent skill at a relative path (../../founder-brand/SKILL.md) to define its voice rubric, which is standard behavior for sub-skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and drafts. While this represents an ingestion surface for untrusted data, the risk is assessed as safe within its intended scope as a writing assistant.
  • Ingestion points: User-provided topics and drafts in Modes A, B, and C.
  • Boundary markers: None present.
  • Capability inventory: Tools for file reading, writing, and searching (Read, Write, Grep).
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:28 PM
Security Audit — agent-trust-hub — linkedin-craft