beginner-pm
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes arbitrary natural language from users to drive automated actions. 1. Ingestion points: User project descriptions and clarifying responses. 2. Boundary markers: Absent; no specific delimiters isolate user input from internal instructions. 3. Capability inventory: The skill is authorized to write code, create and configure files, and execute terminal commands. 4. Sanitization: Absent; no explicit validation or sanitization of user-provided content is mentioned.
- [COMMAND_EXECUTION]: The skill is explicitly instructed to perform autonomous system operations, including running terminal commands and managing file system changes, to fulfill project tasks without manual user intervention.
Audit Metadata