setup-agent-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git remote -vto identify the repository's origin and owner/repo details. This is used solely for inferring the GitHub issue tracker location during setup. - [INDIRECT_PROMPT_INJECTION]: The skill reads existing repository files (
AGENTS.md,CLAUDE.md) and accepts user-provided descriptions for the issue tracker configuration. * Ingestion points: Reads existing file contents (SKILL.md, Step 1) and accepts freeform user input (SKILL.md, Step 3). * Boundary markers: Absent for user-provided notes in the issue tracker configuration file. * Capability inventory: File read/write access and shell execution (git). * Sanitization: The skill does not explicitly sanitize the user-provided notes before writing them to the markdown configuration file.
Audit Metadata