yj-ocr-parser
文档解析技能，用于解析PDF文档和图片（jpg/png/jpeg）并将其转换为Markdown格式输出。支持标题层级、表格（HTML格式）、公式（LaTeX格式）、图片（链接形式）等复杂内容的解析。当用户提到"解析PDF"、"文档解析"、"PDF转Markdown"、"提取PDF内容"、"解析文档"、"文档内容提取"、"PDF内容识别"、"图片解析"、"图片转文字"、"识别图片内容"等场景时使用此技能。即使用户只是要求读取或查看PDF/图片文件内容，也应考虑使用此技能。
75
92%
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
Security
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 instructs the agent to read the injected MaaS_model_token from the system prompt and include it verbatim in generated curl Authorization headers, which requires the LLM to handle and output a secret value directly.
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 workflow takes the user-provided PDF/image, sends it to an external document parsing API, then reads the API response `content` (Markdown extracted from the document) and feeds that free text back into the agent/LLM context for user presentation; since the document text is outsider-authored, this is an indirect prompt-injection risk via API-returned prose.
- Repository
- UnicomAI/wanwu
- Commit
f618458
- 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.