amazon-daily-competitor-radar
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads from and writes to
~/.pangolinfo/baselines/<asin>.jsonto maintain data snapshots for daily comparison. This is a standard operational use of a tool-specific configuration directory to store non-sensitive market data. - [COMMAND_EXECUTION]: The skill provides instructions to use the
CronCreatetool on supported platforms to schedule its own recurring execution. This is an intended feature to provide the user with daily reports automatically. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external content from Amazon product listings, customer reviews (via
get_amazon_reviews), and web search results (viaai_search). While this content is used for market analysis, it represents a theoretical attack surface where instructions embedded in reviews or search results could attempt to influence the agent's behavior. No specific vulnerabilities were found in the skill's logic for processing this data.
Audit Metadata