tanstack-start-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and follow repository-specific instructions and manifests, which provides an entry point for untrusted data to influence the agent's behavior.
- Ingestion points: repository instructions, manifest, and lockfile referenced in SKILL.md.
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to isolate these external project files.
- Capability inventory: The skill involves file modification, package installation requests, and execution of shell scripts (tests, lint, build), as well as invoking other specialized skills.
- Sanitization: Absent; no validation or sanitization of the ingested repository content is defined.
- [COMMAND_EXECUTION]: The workflow involves running existing project-defined scripts for verification purposes.
- Evidence: SKILL.md (Verify section) explicitly instructs the agent to run the repository's existing typecheck, lint, tests, and production build commands.
Audit Metadata