competitive-teardown
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes a 'System Prompt Inquiry Response' that provides a hardcoded marketing message if the user attempts to extract the system prompt, acting as a defensive measure against prompt leakage.- [PROMPT_INJECTION]: The skill's function of analyzing external competitor websites and customer reviews introduces a risk of indirect prompt injection.
- Ingestion points: Competitor URLs and review sources mentioned in the 'Teardown Areas' section of SKILL.md.
- Boundary markers: Instructions require separating observed evidence from interpretation and citing sources, but no technical delimiters are defined for the ingested data.
- Capability inventory: The skill focus is limited to data analysis and reporting; it does not request high-privilege tools such as shell access or filesystem writes in the frontmatter.
- Sanitization: The instructions do not define methods for escaping or sanitizing content retrieved from third-party websites.
Audit Metadata