llm-price-scraper
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses
agent-browserto visit and scrape external LLM provider websites. Because the agent must interpret the content of these pages to extract pricing models and values, an attacker could place malicious instructions on a webpage to influence the agent's behavior or output. - Ingestion points: Untrusted data enters the agent context via
agent-browser snapshot -iinSKILL.mdwhen analyzing provider URLs. - Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions found within the scraped content.
- Capability inventory: The skill has the ability to write files to the local
prices/directory, read and merge JSON files, and execute local Node.js or Python scripts (scripts/merge_prices.js,scripts/merge_prices.py). - Sanitization: No sanitization or validation of the scraped text is performed before it is processed by the agent.
Audit Metadata