amazon-sales-estimator
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Amazon product pages via
web_fetchandweb_searchto extract product details such as BSR, title, and price. This represents a potential indirect prompt injection surface as product content is user-generated and can be controlled by third parties. - Ingestion points: External content is retrieved from Amazon URLs via
web_fetchin Mode B and Mode C as described in SKILL.md. - Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded in the fetched content.
- Capability inventory: The skill's capabilities are limited to
web_fetchandweb_searchfor data retrieval. There are no associated file system writes, remote code executions, or network exfiltration capabilities identified. - Sanitization: The skill relies on the agent's natural ability to selectively extract specific data points from the fetched content rather than implementing structured parsing or explicit sanitization.
- [NO_CODE]: The skill consists exclusively of markdown instructions and configuration. No executable scripts, binaries, or source code files are included in the distribution.
Audit Metadata