ts-testing
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external documentation using research tools (Context7, Exa). This establishes a surface for indirect prompt injection, as instructions found on external web pages could potentially influence the agent's behavior.
- Ingestion points: The Agent Workflow in SKILL.md uses the research-expert step to verify latest documentation via external tools.
- Boundary markers: The skill does not define specific markers or instructions to isolate retrieved documentation from the agent's primary instructions.
- Capability inventory: The skill facilitates file configuration (writing bunfig.toml and vitest.config.ts) and shell command execution (bun test, vitest run).
- Sanitization: No sanitization process is described for the retrieved documentation before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill includes instructions for running test commands such as bun test and npx vitest. These are standard operations for a testing skill and are used in accordance with development best practices.
Audit Metadata