workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
63
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/workflow-runner/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
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 asks for required user inputs and then substitutes those values verbatim into rendered task text, child-agent prompts, and saved output files, so any API keys/passwords provided would be included in the LLM's outputs and persisted.
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
SKILL.md describes reading the user-specified YAML (“用 Read 工具读取用户指定的 YAML 文件”) and role `.md` files (“用 Read 工具读取…角色 `.md` 文件”) and then injecting the rendered task plus the full role system prompt/markdown into sub-agents’ prompts and step execution context; if those files come from outsider-authored sources (e.g., role directory installed from an external npm/git package or user-provided YAML/docs), the LLM receives that free text at runtime.
- Repository
- jnMetaCode/superpowers-zh
- Commit
12a4dc1
- 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.