product-marketing

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads project-level files such as README.md, package.json, and marketing copy to auto-draft context. This is limited to information necessary for the skill's primary function and occurs locally within the user's workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository files during the auto-drafting process.
  • Ingestion points: Reads README, landing pages, marketing copy, package.json, and other documentation in the repository (SKILL.md).
  • Boundary markers: None present; the agent is instructed to study the repo and draft the document.
  • Capability inventory: The agent has capabilities to read repository files and write the .agents/product-marketing.md file. It does not invoke shell commands or network tools based on this data.
  • Sanitization: No specific sanitization or filtering of the ingested content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:30 AM
Security Audit — agent-trust-hub — product-marketing