amazon-bestseller-listing
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a Python script (
scripts/extract-bestseller.py) to generate JavaScript that extracts structured data from the DOM of Amazon bestseller pages. The extracted data (rank, ASIN, title, price, etc.) is consistent with the skill's stated purpose. - [COMMAND_EXECUTION]: The skill utilizes
browser-actto evaluate JavaScript within the browser. The commands used (browser-act --session {name} eval "$(python scripts/extract-bestseller.py)") are standard for skills requiring DOM interaction. The use of bash command substitution here is for passing the script's output as an argument and does not present an injection risk as the input is a static local file. - [DATA_EXFILTRATION]: No network operations to external or untrusted domains were found. The skill processes data locally within the agent's context and browser session. The extracted product data is returned to the user as intended.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials or attempts to access sensitive system files (like SSH keys or AWS configs) were identified. The skill explicitly states it requires no login to function.
- [PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override agent behavior, bypass safety filters, or extract system prompts. The 'Important' markers found in the documentation are used for legitimate technical guidance.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or package installations at runtime. It relies on its own provided scripts and the existing environment.
Audit Metadata