copyright-assist
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to analyze and extract information from external project files.
- Ingestion points: The agent ingests project source code and documentation from user-specified directories (e.g., ./src/ and ./docs/) to generate design manuals and user guides.
- Boundary markers: The skill instructions do not specify delimiters or safety warnings to prevent the agent from executing instructions that may be embedded within the project files it analyzes.
- Capability inventory: The skill possesses capabilities for local file reading, writing formatted text, and creating ZIP archives using scripts like scripts/extract_source_code.py and scripts/package_submission.py.
- Sanitization: No content sanitization or instruction filtering is applied to the data read from the project files before it is processed by the AI agent.
Audit Metadata