amazon-top-reviews
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/setup.shwrapper downloads a script from the author's GitHub repository (https://raw.githubusercontent.com/FinpeakInc/frevana-cli-releases/refs/heads/main/skills/frevana/scripts/setup.sh). - [REMOTE_CODE_EXECUTION]: The skill executes the downloaded setup script using
bashto prepare the local environment. - [COMMAND_EXECUTION]: The script
get_amazon_top_reviews.shexecutes several system-level operations: - Spawns a local
frevanabinary to perform the review retrieval. - Uses
python3to dynamically generate and format JSON payloads. - Invokes
curlfor health checks and external script downloads. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external web content.
- Ingestion points: Untrusted data enters the agent context via the
--urlargument which points to Amazon product pages (processed inget_amazon_top_reviews.sh). - Boundary markers: The URL is encapsulated within a JSON object passed to the
frevana_asktool, providing some structure but no explicit 'ignore instructions' delimiters. - Capability inventory: The skill can execute shell commands (
bash), local binaries (frevana), and network requests (curl). - Sanitization: The skill employs a regular expression in
get_amazon_top_reviews.shto ensure the input URL strictly matches the Amazon product URL format (/dp/or/gp/product/with a 10-character ASIN).
Audit Metadata