marketing-psychology

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of static informational text and advisory instructions. It does not contain any executable scripts, binary files, or network-enabled commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by reading project-specific context files.
  • Ingestion points: The skill reads data from .claude/product-marketing-context.md (referenced in SKILL.md).
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore potentially malicious directions within the context file.
  • Capability inventory: The skill has no high-risk capabilities such as command execution (subprocess/shell), network access, or file-writing permissions.
  • Sanitization: No content sanitization or structured validation is applied to the ingested context data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:21 PM