shunk031-manage-public-private-skills
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands
DOTFILES_SKILLS_FORCE_UPDATE=1 chezmoi applyandmake skills-update. These are used to reconcile and update the installed skills on the local machine as part of the intended development workflow.\n- [INDIRECT_PROMPT_INJECTION]: Since the skill's purpose is to manage and edit other skills, it inherently interacts with untrusted data in the form of third-party or user-created skill content. This presents an attack surface where instructions embedded in those files could influence the agent.\n - Ingestion points: The agent is instructed to read, compare, and edit skill source files within repository worktrees (SKILL.md).\n
- Boundary markers: There are no specific delimiters or ignore-instructions markers used when processing external skill content.\n
- Capability inventory: The skill utilizes shell command execution (
chezmoi,make) and file system write access to local repository checkouts (SKILL.md).\n - Sanitization: No explicit sanitization or validation of the content within managed skills is described.
Audit Metadata