kmp-snapshot-testing-setup

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (cp, chmod, find, sed) to set up the project environment and perform string replacements. This is standard behavior for a setup utility but involves direct interaction with the host filesystem.\n- [PROMPT_INJECTION]: The skill instructions in SKILL.md define an attack surface for indirect prompt injection by interpolating user-provided inputs (project paths, package names) into shell commands without explicit boundary markers or sanitization logic.\n
  • Ingestion points: User project paths and package names provided during the setup process in SKILL.md.\n
  • Boundary markers: Absent in the shell command templates.\n
  • Capability inventory: Shell command execution (sed, find, cp, chmod) and filesystem write operations across multiple scripts.\n
  • Sanitization: Absent; the skill relies on the agent's internal handling of interpolated variables.\n- [EXTERNAL_DOWNLOADS]: The skill configuration adds dependencies on well-known testing libraries (Kotest, Turbine) to the project's build files. These downloads are performed by standard build tools and target official package registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 11:45 PM