design
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
Bashto perform environment discovery, specifically listing agent types and command plugins located in~/.claude/commands/. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it incorporates untrusted data from user arguments and local source files into the context for its
plannerandarchitectsub-agents. - Ingestion points: User-provided requirements (
$ARGUMENTS) and project source files (accessed viaRead,Glob, andGrep). - Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands when passing data to sub-agents.
- Capability inventory: The skill has powerful capabilities including shell command execution (
Bash), file modification (Edit,Write), and task delegation to other agents (Agent). - Sanitization: There is no evidence of sanitization or validation of external content before it is processed by the sub-agents.
Audit Metadata