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/**/*.mdand~/.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
Agenttool 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 agentscommand 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