pricing-page-psychology-audit
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes content from external websites provided by the user.
- Ingestion points: Data enters the agent context via the
scripts/scrape_pricing.pyscript, which fetches content from any user-provided URL. - Boundary markers: The instructions in
SKILL.mdlack explicit delimiters or instructions to ignore embedded commands within the scraped text. - Capability inventory: The skill utilizes local subprocess execution to run the Python scraper and performs network requests using the
requestslibrary. - Sanitization: The scraped content is passed directly to the AI for analysis without filtering or sanitization of potentially malicious instructions embedded in the target page's text.
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/scrape_pricing.pyas part of its core workflow defined inSKILL.md. This is the intended behavior for extracting page data for analysis. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to external URLs provided by the user to retrieve pricing page content. This functionality is essential to the skill's purpose and uses standard browser-like headers to facilitate scraping.
Audit Metadata