claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
68
81%
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
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The content includes explicit, authoritative directives (e.g., "ALWAYS use claude-opus-4-6" / "This is non-negotiable") and documents options to bypass permission prompts (e.g., "bypassPermissions" with allow_dangerously_skip_permissions), which weakens security/user consent boundaries and constitutes suspicious steering without clear malicious intent.
Low
Low-risk findings.
2 low severity findings. 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 the required runtime workflow, the agent is driven by a caller-provided `prompt` string passed into `claude_agent_sdk.query()` (and subsequent agent turns/messages), which is outsider-authored free text and is directly ingested by the LLM.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly calls out using WebFetch at runtime to pull live documentation (e.g., https://platform.claude.com/docs/en/about-claude/models/overview.md) and lists many WebFetch/raw-GitHub URLs whose fetched content would be injected/extracted to drive prompts, so these URLs are runtime dependencies that can directly control agent prompts.
- Repository
- UnicomAI/wanwu
- Commit
030c20b
- 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.