product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary functionality is to assist the user in documenting business positioning and messaging. It reads local files (such as README and package.json) to generate a draft and writes the output to a local markdown file. No network activity or sensitive data exfiltration was identified.- [PROMPT_INJECTION]: The skill contains a feature to auto-draft content by reading the codebase, which presents a surface for indirect prompt injection.
  • Ingestion points: Scans README, package.json, marketing copy, and landing pages within the repository.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the scanned files.
  • Capability inventory: The skill is limited to reading local files and writing a single markdown file to the .agents/ directory. It does not have access to shell execution, network tools, or administrative privileges.
  • Sanitization: No specific content sanitization or validation logic is defined for the ingested text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:27 PM
Security Audit — agent-trust-hub — product-marketing-context