test
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external task files to determine verification steps. Ingestion points: Resolves and reads task documentation from docs/task/{ID}-{task-name}.md and project context from AGENTS.md. Boundary markers: Absent; there are no instructions to the agent to disregard embedded commands or use delimiters for data from the task files. Capability inventory: Executes shell commands for unit, integration, API, and CLI testing, and performs file system writes to docs/testing/. Sanitization: Absent; the skill does not specify validation or filtering of the content read from task documents.
- [COMMAND_EXECUTION]: The skill's primary function is to execute arbitrary project-defined commands, including unit/integration tests and browser automation tools, which may pose a risk if the project environment or task definitions are compromised.
Audit Metadata