team-builder

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by reading persona definitions from external markdown files and interpolating them directly into the instructions for spawned sub-agents.\n
  • Ingestion points: Reads files from ./agents/**/*.md and ~/.claude/agents/**/*.md.\n
  • Boundary markers: Absent. The skill does not wrap the imported persona content in delimiters or provide instructions to the sub-agent to ignore embedded commands.\n
  • Capability inventory: The skill uses the Agent tool to spawn and execute sub-agents in parallel.\n
  • Sanitization: Absent. Content from the markdown files is used without validation or escaping.\n- [COMMAND_EXECUTION]: The skill executes the claude agents command to discover available agents within the user's environment. This is the primary discovery mechanism and is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — team-builder