do-and-judge
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
70%
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 ./plugins/sadd/skills/do-and-judge/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 runtime workflow ingests outsider-authored free-form text from the user’s `task` argument into both the meta-judge and judge prompts (and passes the task-derived evaluation spec), enabling prompt-injection via crafted task instructions.
- Repository
NeoLabHQ/context-engineering-kit
- Revision
23e2428
- 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.