prioritize-reference-files
Ensures agents read and use provided reference files before searching or fabricating data
45
56%
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/prioritize-reference-files/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
This skill’s required workflow reads “reference files provided in task context” (Step 2 via `read_file(...)` and potentially `.docx` fallback extraction that outputs extracted XML/text), which can be outsider-authored attachments forwarded by someone other than the operating user and then ingested as readable prose into the agent’s LLM context.
- 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.