tanstack-start-deployment
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze local project files, such as
../../docs/deployment-and-observability.md, package scripts, and runtime configurations. These files represent an attack surface where malicious instructions could be embedded to influence the agent's behavior. - Ingestion points: The agent reads external documentation and local project configuration files (specified in
SKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious content within the analyzed files.
- Capability inventory: The skill allows for building production output, running server artifacts, and validating environment variables.
- Sanitization: While the skill emphasizes protecting secrets, it does not specify sanitization or validation logic for the content of the documentation it reads.
- [COMMAND_EXECUTION]: The skill requires the agent to execute build commands and run server artifacts locally to verify the production build. This is a standard and intended function for a deployment preparation skill, and the instructions include a safety constraint requiring explicit approval before performing remote deployments or modifying secrets.
Audit Metadata