web-renderer-test
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user requests to generate React components (fixtures) and test code, which presents a surface for instructions embedded in user data to influence agent behavior.
- Ingestion points: User-provided descriptions of test changes and component structures (as described in
SKILL.md). - Boundary markers: Absent; there are no explicit instructions for the agent to ignore or delimit potentially malicious code within user requests.
- Capability inventory: The skill utilizes file-writing capabilities across multiple directories (
packages/web-renderer/src/test/,packages/docs/docs/) and command execution viabunx(inSKILL.md). - Sanitization: Absent; the instructions do not specify validation or sanitization of user-provided code or documentation updates.
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to verify test results.
- Evidence:
SKILL.mdexplicitly instructs the use ofbunx vitest src/test/video.test.tsxto run the test suite.
Audit Metadata