competitor-analysis
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs local file read operations to load brand context and marketing SOPs from a specific directory (~/.claude-marketing/). These operations are necessary for generating tailored reports and are restricted to the application's data path.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of processing content from external competitor URLs provided by the user. \n
- Ingestion points: Competitor URLs provided as user input for analysis. \n
- Boundary markers: The instructions do not define specific delimiters or guidelines to ignore instructions found within the scraped external content. \n
- Capability inventory: Local file read access for brand context and implied network access for external data gathering. \n
- Sanitization: No specific sanitization or filtering of external content is mentioned before processing.
Audit Metadata