delegation-check
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs the Bash tool to execute grep and ls commands for discovering and searching within codebase files (e.g., .claude/commands/ and .claude/agents/). This is a core part of its diagnostic functionality and is used to extract Agent() calls and role definitions.
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted data from the repository.
- Ingestion points: Reads content from local repository files, including .workflow/codebase/ARCHITECTURE.md, command files, and agent definitions.
- Boundary markers: The instructions do not specify the use of robust boundary markers or 'ignore instructions' warnings when interpolating the content of these files into the agent's context for analysis.
- Capability inventory: The skill has access to Bash, Read, Grep, Glob, and AskUserQuestion tools.
- Sanitization: There is no evidence of sanitization or filtering of the content read from the codebase before processing. If the analyzed files contain malicious instructions, they could potentially influence the behavior of the agent during the evaluation process.
Audit Metadata