setup-devcraft
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project root, including markdown tickets and configuration files (
AGENTS.md,CLAUDE.md). - Ingestion points: Project root, installed skill directories,
AGENTS.md,CLAUDE.md, repository commands, documents, and tickets (SKILL.md steps 1 and 3). - Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore embedded instructions in the processed data.
- Capability inventory: File inspection, updating
AGENTS.mdin place, and running an "adapter installer" (SKILL.md steps 2 and 3). - Sanitization: Absent. The skill does not describe any validation or filtering of the content read from external files.
- [COMMAND_EXECUTION]: The instructions direct the agent to run an "adapter installer" if the installation is incomplete and a source checkout is available (SKILL.md step 2). This involves executing local scripts provided with the DevCraft collection to facilitate project setup.
Audit Metadata