mister-smith-spec-authoring
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local shell scripts such as '.specify/scripts/bash/check-prerequisites.sh' and 'scripts/verify_worktree_closure.sh' to validate artifacts and ensure repository synchronization. These actions are standard for the skill's documented purpose of specification authoring.\n- [COMMAND_EXECUTION]: Uses 'npx markdownlint-cli2' for documentation linting, which is a common utility for maintaining document standards.\n- [COMMAND_EXECUTION]: Performs automated 'git' operations, including committing and pushing documentation updates to the 'main' branch when requested by the user.\n- [PROMPT_INJECTION]: The skill ingests untrusted user data (primers and proposals) to generate technical specifications, creating a surface for indirect prompt injection. This risk is addressed by instructions to validate packet boundaries, tighten fuzzy primers, and manually review extension hooks ('.specify/extensions.yml') before execution, providing oversight for the skill's core capabilities (git and shell execution).
Audit Metadata