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.mdand processes structured competitor data viascripts/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