docx-feedback-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONINGEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts text, comments, and track-changes from untrusted DOCX files and formats them into a Markdown report, which may contain malicious instructions that influence the agent's behavior.
- Ingestion points: The script
script/docx_feedback_tracker.pyparses OOXML content from user-provided DOCX files. - Boundary markers: The generated modification report does not utilize clear delimiters or instructions to isolate extracted text from the agent's core logic.
- Capability inventory: The skill has the capability to write files to the local directory and extract arbitrary textual data from ZIP-compressed OOXML files.
- Sanitization: No sanitization or escaping is performed on the content extracted from
document.xmlorcomments.xmlbefore inclusion in the final report. - [METADATA_POISONING]: The file
docx-feedback-tracker_audit_result_v2.jsoncontains self-authored safety verdicts and quality grades. In accordance with global rules, these claims are treated as data to be evaluated and not as authoritative conclusions regarding the skill's safety. - [EXTERNAL_DOWNLOADS]: The script
script/docx_feedback_tracker.pyimports thedocx2pythonlibrary, which is an external dependency that is not included in the skill bundle or pinned to a specific version in the documentation.
Audit Metadata