recipe-add-integration-tests

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by discovering and reading project documentation files, which serve as context for automated test generation and implementation sub-agents.
  • Ingestion points: The skill reads files from docs/design/, docs/ui-spec/, and docs/prd/, as well as paths provided via $ARGUMENTS.
  • Boundary markers: There are no explicit instructions to enclose external content in boundary markers or to ignore instructions embedded within these files.
  • Capability inventory: The skill triggers multiple sub-agent invocations (acceptance-test-generator, task-executor, integration-test-reviewer, quality-fixer) and executes git commits through the Bash tool.
  • Sanitization: No sanitization, validation, or filtering of the ingested document content is described in the workflow.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool in Step 7 to execute git commit commands for saving the generated integration test files to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 10:09 AM
Security Audit — agent-trust-hub — recipe-add-integration-tests