office-remediator
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and executes Python scripts to remediate accessibility issues in .docx, .xlsx, and .pptx files. This dynamic script generation is driven by the results of external document audits.
- [EXTERNAL_DOWNLOADS]: The skill relies on several well-known Python libraries for document manipulation, including
python-docx,openpyxl,python-pptx, andlxml. These are established packages used within the community for these specific tasks. - [PROMPT_INJECTION]: The skill is designed to process an external audit report (
DOCUMENT-ACCESSIBILITY-AUDIT.md), which creates a potential surface for indirect prompt injection. - Ingestion points: Untrusted data enters the agent context through the reading of the
DOCUMENT-ACCESSIBILITY-AUDIT.mdfile. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate the data in the audit report from the agent's logic.
- Capability inventory: The skill has permissions to read and write files on the local filesystem and to execute Python code it generates.
- Sanitization: There is no mention of validating or sanitizing the content of the audit report before it is used to determine the logic of the generated remediation scripts.
Audit Metadata