competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation and instructional templates. It contains no executable scripts, system commands, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to generate content based on user-provided competitor information, which represents an attack surface for indirect prompt injection. A user could potentially include malicious instructions within the competitor data fields to influence the agent's output.
- Ingestion points: User-supplied product names, features, and descriptions across SKILL.md templates.
- Boundary markers: No explicit delimiters are used to separate user data from the generation instructions.
- Capability inventory: Limited to the generation of marketing copy and structured data (YAML/Markdown).
- Sanitization: The instructions do not define validation or sanitization steps for the input data.
Audit Metadata