rpi-setup-humanlayer

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses several shell commands to validate the environment and prepare the workspace, including which, humanlayer, linear, git, and standard filesystem tools like mkdir and ls. These are standard operations for a development-oriented setup skill within the vendor's ecosystem.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it handles external data.
  • Ingestion points: Content is fetched from an external source via linear get-issue eng-1234 in SKILL.md.
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands when writing the ticket data to ticket.md.
  • Capability inventory: The skill can create directories, write to the filesystem via redirection, and execute environment-aware shell commands.
  • Sanitization: No sanitization, escaping, or validation is performed on the data retrieved from the Linear API before it is stored and passed to subsequent agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 03:45 AM
Security Audit — agent-trust-hub — rpi-setup-humanlayer