competitor-alternatives

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (competitor features, pricing, and reviews) to generate marketing copy and comparison matrices. This creates a surface for indirect prompt injection if the source data contains malicious instructions meant to subvert the agent's behavior during content generation.\n
  • Ingestion points: The skill reads product marketing context from .claude/product-marketing-context.md and processes structured competitor data via scripts/comparison_matrix_builder.py.\n
  • Capability inventory: The Python script generates Markdown comparison tables, and the agent is instructed to write full marketing page copy.\n
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are utilized in the provided templates or script outputs to isolate untrusted external data.\n
  • Sanitization: The skill lacks explicit sanitization or validation logic to filter out potential prompt injection strings from the external research data it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — competitor-alternatives