tw-edu-parent-communication
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute a local Python script (scripts/generate_parent_comm.py) which generates .docx files in the/mnt/user-data/outputs/directory based on teacher input.\n- [PROMPT_INJECTION]: The skill is susceptible to an indirect prompt injection surface inSKILL.md. The user-provided summary is interpolated directly into a shell command (--content "[主要訊息摘要]").\n - Ingestion points: User input for the
[主要訊息摘要]placeholder in the generation command.\n - Boundary markers: The placeholder is wrapped in double quotes in the shell script block.\n
- Capability inventory: The skill has
Bash,Read, andWritetool permissions, allowing it to execute scripts and write to the filesystem.\n - Sanitization: No explicit validation or sanitization of the input string is performed before it is passed to the shell execution environment.
Audit Metadata