start-feature

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run various CLI utilities such as git, bd (Beads), and wt (Worktree). It also executes Python scripts like resolve-feature.py from the sibling directory ../dstack-core using uv run.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx skills update to communicate with the npm registry for package updates.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) through its review workflow. Ingestion points: It reads project files including design.md and source code. Boundary markers: No explicit delimiters or instructions are used to isolate file content from the agent's instructions. Capability inventory: The agent has access to powerful tools like Bash, Edit, and Write. Sanitization: The content from repository files is not sanitized before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 11:29 AM
Security Audit — agent-trust-hub — start-feature