dev-flow
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to manage git worktrees for development task isolation.\n
- Evidence: The 'Protocol' section of
SKILL.mdoutlines the use ofgit worktree addto create task-specific branches and environments.\n- [INDIRECT_PROMPT_INJECTION]: The skill acts as an automated routing engine for tasks described by users or defined in repository files, creating a potential vector for instructions to influence the tool chain.\n - Ingestion points: Task descriptions provided by the user and files read from the
docs/intent/directory.\n - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the ingested content.\n
- Capability inventory: The skill can execute shell commands and invoke a wide variety of other specialized skills via the
Skilltool.\n - Sanitization: No explicit sanitization or validation logic is defined for the ingested task data or derived branch slugs.
Audit Metadata