website-refactor
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npxto install required teammate skills and usescurlto validate SEO redirects by checking HTTP status codes. - [EXTERNAL_DOWNLOADS]: Downloads and installs three companion skills (
content-extraction,web-audit,seo-migration) from the author's (saccoai) repository usingnpx. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it crawls an external, user-provided URL (
{ORIGINAL_URL}) and passes the extracted content to other agents for processing. - Ingestion points: Data enters the environment via the
content-extractorteammate which crawls an external website and saves content tocontent-inventory.mdandsrc/data/. - Boundary markers: Absent. The prompts for the
designerandcontent-extractoragents do not include delimiters or instructions to ignore potential commands embedded in the source website's content. - Capability inventory: The agent team has the ability to write to the project's source code (
src/,app/), manage public assets, and perform network requests viacurlandPlaywright. - Sanitization: There is no evidence of sanitization or filtering of the extracted website content before it is interpreted by the
designeragent during page implementation.
Audit Metadata