offers

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is comprised entirely of educational Markdown files. There are no scripts, binaries, or command-line instructions provided for execution. All internal references target other documentation files within the same skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest context from external workspace files such as .agents/product-marketing.md. While this introduces a data ingestion surface for potentially untrusted data, the skill possesses no dangerous capabilities—such as file writing, shell access, or network requests—that could be leveraged by a malicious instruction in the ingested data. * Ingestion points: SKILL.md (instructions to read project-specific marketing context files). * Boundary markers: None provided in the skill's instructions. * Capability inventory: None detected. The skill's primary function is providing text-based consulting advice. * Sanitization: None defined in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:07 PM