coffee-break
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local PowerShell script named
check.ps1as part of its verification loop. - [PROMPT_INJECTION]: The skill processes untrusted project data (codebase and source files) which exposes the agent to indirect prompt injection vulnerabilities.
- Ingestion points: The skill analyzes the 'current codebase' and 'related source code' based on user references in SKILL.md.
- Boundary markers: There are no specific delimiters or instructions provided to separate code data from agent instructions.
- Capability inventory: The skill allows for executing a plan, modifying files, and running the
check.ps1script as defined in SKILL.md. - Sanitization: No evidence of input validation, escaping, or sanitization is present before the agent processes external project files.
Audit Metadata