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_fetch and web_search to 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_fetch in 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_fetch and web_search for 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
Risk Level
SAFE
Analyzed
Sep 29, 2026, 01:51 PM