devtu-benchmark-harness
Continuous improvement system for ToolUniverse tools, skills, and plugin. Run benchmarks, diagnose failures, route fixes to devtu skills, retest. Use after skill optimization, tool additions, or as regression check.
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: 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
In `scripts/run_eval.py`, the runner loads question text from `skills/evals/*/questions.json` (or an attacker-supplied `--data-file`), then builds a prompt with that free text and passes it to Claude Code at runtime via `prepare_prompt()` → `run_claude()`, meaning outsider-authored question content is directly ingested by the agent before it routes/executes tools.
- Repository
- mims-harvard/ToolUniverse
- Commit
089eb8e
- 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.