docx-dual-parse
Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback
54
68%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./benchmarks/gdpval/skills/docx-shell-parse-enhanced-4bba79/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow parses the DOCX by extracting `word/document.xml` from a user-supplied `.docx` (public/untrusted document content) and then runs shell/Python to strip tags; that extracted XML is free text from an outsider and becomes part of the LLM context via the tool’s returned output.
- Repository
- HKUDS/OpenSpace
- Commit
3827781
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.