document-skills
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (HIGH): The skill is designed to ingest and process untrusted external data in the form of documents, which is a high-risk capability. Ingestion points: Processes .docx, .pdf, .pptx, and .xlsx files. Boundary markers: There are no specified delimiters or instructions to the agent to disregard commands found within the processed documents. Capability inventory: The skill claims capabilities to create and edit documents and manipulate spreadsheet formulas, which provides a significant impact vector for any successful injection. Sanitization: No sanitization or content validation logic is defined in the manifest.
- No Code (LOW): This manifest file is purely documentation and does not contain any direct executable scripts, shell commands, or encoded payloads.
Recommendations
- AI detected serious security threats
Audit Metadata