competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill package is composed entirely of instructional Markdown and YAML templates. It contains no executable code, shell scripts, or binary files.- [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for untrusted data, though this is integral to its research-focused purpose.
- Ingestion points: The skill instructs the agent to read local files (
.claude/product-marketing-context.md) and perform web research on third-party review sites. - Boundary markers: No explicit delimiters or boundary instructions are provided for the agent to separate user/competitor data from instructions.
- Capability inventory: The skill is designed for text generation based on file reads and web research.
- Sanitization: The instructions do not define validation or sanitization routines for external data.
Audit Metadata