marketing-selling-point-generator

Warn

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions require cloning a repository from an unverified GitHub user account (danidai098-arch/marketing-selling-point-generator.git). This source is not associated with the primary vendor or any recognized trusted organization, presenting a supply chain risk.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted external data.
  • Ingestion points: The analyzeReviews method in SKILL.md takes a raw array of user-provided review strings for analysis.
  • Boundary markers: There are no delimiters or instructions provided to the agent to ignore or isolate potentially malicious commands embedded within the review data.
  • Capability inventory: The skill uses high-capability tools including the CopyWriter (which interfaces with OpenAI's API) and file export utilities (exportToCSV, exportToJSON).
  • Sanitization: No input validation, escaping, or filtering logic is present in the provided documentation or code snippets to handle adversarial content in the input data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 12, 2026, 07:44 PM
Security Audit — agent-trust-hub — marketing-selling-point-generator