product-marketing

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on untrusted codebase data for document generation.\n
  • Ingestion points: The agent reads the README, landing pages, marketing copy, and package.json files to auto-draft the marketing context (Step 2).\n
  • Boundary markers: The skill lacks delimiters or explicit instructions to treat the ingested codebase content as potentially untrusted data.\n
  • Capability inventory: The agent has the capability to read repository files and write the resulting context to .agents/product-marketing.md.\n
  • Sanitization: No methods for sanitizing, escaping, or validating the content retrieved from the project files are provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:21 PM
Security Audit — agent-trust-hub — product-marketing