Forums

Articles
Create
cancel
Showing results for 
Search instead for 
Did you mean: 

Why Rovo Agent cannot read images embedded inside file attachments (XLSX, PDF, DOCX)?

Esteban Malano _Appricity_
I'm New Here
I'm New Here
Those new to the Atlassian Community have posted less than three times. Give them a warm welcome!
June 16, 2026

Current behavior:
Rovo Agents can read images when they are attached directly to a Jira issue as standalone image files (JPG, PNG, etc.).

However, when images are embedded inside file attachments (e.g., an XLSX with 3 embedded images, a PDF with screenshots, a DOCX with diagrams), Rovo cannot extract or interpret that visual content.

Expected behavior:
Rovo Agents should be able to extract and interpret images embedded inside file attachments, using the same vision capabilities already available for standalone image attachments.

Why this matters:
In real workflows, users attach documents (XLSX reports, PDF specs, DOCX requirements) that contain images as the primary content. The agent receives no information from these files, blocking AI-assisted analysis entirely.

Evidence:
Tested with an XLSX file containing 3 embedded images — openpyxl confirms the images exist (ws._images = 3) but Rovo returns no visual content from the file.

1 answer

1 accepted

3 votes
Answer accepted
Jason Krewson
Rising Star
Rising Star
Rising Stars are recognized for providing high-quality answers to other users. Rising Stars receive a certificate of achievement and are on the path to becoming Community Champions.
June 16, 2026

I think this is due to Rovo Agents only being able to process direct image attachments, they can't like open the files to see the attachment. 

Where did you get the "expected behavior" information from?

Esteban Malano _Appricity_
I'm New Here
I'm New Here
Those new to the Atlassian Community have posted less than three times. Give them a warm welcome!
June 16, 2026

The expected behavior is what we want Rovo agents to support: the ability to read and process images embedded inside file attachments. This would allow agents to extract and analyze visual content from common office files without requiring manual preprocessing. We're requesting this as a feature enhancement.

Also, do you have any insight into why this hasn't been implemented yet? Is it a technical limitation on Rovo's end, a model limitation, or is it simply not yet prioritized on the roadmap?. 

Thanks for looking into this!

Like Jason Krewson likes this
Jason Krewson
Rising Star
Rising Star
Rising Stars are recognized for providing high-quality answers to other users. Rising Stars receive a certificate of achievement and are on the path to becoming Community Champions.
June 16, 2026

Oh I see, yeah this sounds like a great feature suggestion, for that check out the options below. 

Like Fazila Ashraf likes this
Dr Valeri Colon _Connect Centric_
Community Champion
June 16, 2026

Suggest an answer

Log in or Sign up to answer
TAGS
AUG Leaders

Atlassian Community Events