css-scroll-driven-native
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from a project's
design.mdfile to adapt styling tokens in generated CSS, which could allow instructions embedded in that file to influence the agent. \n - Ingestion points:
design.md(referenced in the input contract and workflow step W03). \n - Boundary markers: Absent; the skill does not define delimiters or provide instructions to ignore embedded commands in the source data. \n
- Capability inventory: The skill has capabilities to write CSS/HTML files and execute browser-based testing via
playwright-verifyas described inSKILL.md. \n - Sanitization: Absent; no validation or escaping of the ingested design data is specified. \n- [COMMAND_EXECUTION]: The skill utilizes the
playwright-verifycapability to execute verification tests in a Chromium browser environment (RULE-05 and W04).
Audit Metadata