afk-setup-project
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from user-provided conversations, briefs, and external specifications to drive its scaffolding and execution logic.
- Ingestion points: Reads conversation history, project briefs, specifications, and existing project files (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions within the ingested data are defined.
- Capability inventory: The skill can initialize project registries, scaffold new files, and execute build, lint, and typecheck commands (SKILL.md).
- Sanitization: The instructions do not specify any validation or sanitization of the input data before it influences system commands and configuration.
- [COMMAND_EXECUTION]: The skill performs project initialization and verification by executing shell commands.
- Evidence: The agent is instructed to 'scaffold the project, initialize its registries, and configure the required checks' and 'Run the configured lint, formatting, typecheck, and build checks' using official tooling (SKILL.md).
Audit Metadata