onboard

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection (Category 8) as it processes untrusted local codebase data.
  • Ingestion points: The agent reads file names and content from the local project directory via find and specific manifest files like package.json and requirements.txt (SKILL.md).
  • Boundary markers: Absent; the instructions do not command the agent to ignore or delimit instructions found within the analyzed files.
  • Capability inventory: The agent can execute shell commands (mkdir, find, tldr) and write YAML handoff files to the local filesystem (SKILL.md).
  • Sanitization: Absent; data harvested from project files is interpolated into a YAML handoff without explicit validation or escaping.
  • COMMAND_EXECUTION (SAFE): The skill uses standard utilities (mkdir, find, tldr) for codebase discovery and directory structure initialization. These operations are consistent with the skill's primary purpose and do not involve piping remote content to a shell or acquiring elevated privileges.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM