competitor-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted data from external sources.
- Ingestion points: The
scripts/competitor_analyzer.pyscript fetches product titles, brand names, and category data from external Amazon Search and Keepa API endpoints. - Boundary markers: Absent. The markdown report structure defined in
SKILL.mddoes not use delimiters or explicit instructions to the agent to ignore or isolate instructions found within the retrieved data. - Capability inventory: The skill is configured with
allowed-tools: [Bash, Read, Write]. This high level of system access increases the potential impact if the agent incorrectly executes instructions embedded in product data. - Sanitization: Absent. The script performs no escaping or filtering of the retrieved API data before interpolating it into the final markdown output presented to the agent.
Audit Metadata