file-naming
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality.\n
- Ingestion points: The skill instructs the agent to analyze files using OCR, text extraction, and vision analysis to derive naming metadata (SKILL.md).\n
- Boundary markers: There are no boundary markers or explicit safety instructions to prevent the agent from being influenced by instructions embedded within the analyzed file content.\n
- Capability inventory: The agent is authorized to perform file renaming operations based on the data it extracts from user-provided files.\n
- Sanitization: No sanitization or verification steps are included to ensure that extracted metadata is free of malicious instructions before it is used for file operations.\n- [NO_CODE]: The skill does not contain any executable code, scripts, or binary dependencies, relying entirely on natural language instructions for the agent.
Audit Metadata