landing-page
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a local Python helper script (
brand_context.py) located in a relative sibling directory (../start-here/scripts/) to initialize brand-specific data. - [INDIRECT_PROMPT_INJECTION]: The TEARDOWN mode utilizes web scraping capabilities to ingest text from arbitrary user-provided URLs, creating a vulnerability surface where malicious instructions on a website could influence the agent's audit results.
- Ingestion points: Scraped content from live URLs via the web-scrape tool and Firecrawl API.
- Boundary markers: None; the instructions do not include specific delimiters or warnings to ignore instructions found within the scraped website data.
- Capability inventory: The skill can execute shell commands (python3) and perform file system writes to create project folders.
- Sanitization: None; the skill does not specify any filtering or validation for the scraped content before it is processed for the conversion audit.
Audit Metadata