llm-price-scraper
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to visit and analyze external web pages provided by the user, which presents a surface for indirect prompt injection attacks where a malicious site could influence the agent's logic.
- Ingestion points: The skill uses
agent-browser open <url>andagent-browser snapshot -iinSKILL.mdto bring external content into the agent's context. - Boundary markers: There are no explicit delimiters or instructions provided in the
SKILL.mdworkflow to mandate that the agent ignore potential instructions embedded within the scraped page content. - Capability inventory: The skill possesses the capability to interact with pages (via
agent-browser click) and perform file system writes and reads (via thenode scripts/merge_prices.jsexecution mentioned inSKILL.md). - Sanitization: The skill lacks any mechanism to sanitize or filter external content before it is processed by the agent for data extraction.
Audit Metadata