do-in-parallel
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
62
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./plugins/sadd/skills/do-in-parallel/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The skill contains explicit, repeated instructions to embed an environment variable (CLAUDE_PLUGIN_ROOT) into prompts sent to sub-agents (i.e., remote LLMs) — a clear data‑exfiltration vector — and also directs the orchestrator to avoid reading full judge reports (parse only headers), which can deliberately hide evidence and obstruct oversight.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires inserting the resolved environment variable CLAUDE_PLUGIN_ROOT (CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT}) into prompts sent to sub-agents, forcing the LLM to emit an environment value verbatim which could expose sensitive secrets if that variable contains them.
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
The required runtime workflow ingests the user-provided free-form `task` text into the “Meta-judge Dispatch” and “Phase 4: Construct Per-Target Prompts” as “User Prompt as Context,” then dispatches meta-judges/judges based on it.
- Repository
- NeoLabHQ/context-engineering-kit
- Commit
8539779
- 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.