repurpose-pinterest

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill acts on untrusted data from the user or parent agents, which is an inherent risk for indirect prompt injection where malicious instructions could be hidden in the source atoms or URLs.
  • Ingestion points: Input data enters via the atoms variable (from parent agent) and the url-or-atoms argument (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted data from the skill's system instructions.
  • Capability inventory: The skill has file system write access to the pinterest/ directory to save generated pins, scripts, and board suggestions (SKILL.md).
  • Sanitization: There is no evidence of content sanitization or instruction filtering before processing input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:53 PM
Security Audit — agent-trust-hub — repurpose-pinterest