web-to-markdown
웹페이지 URL을 입력받아 마크다운 형태로 변환하여 저장합니다. 웹 문서를 로컬 마크다운 파일로 아카이빙하거나 정리할 때 유용합니다.
42
42%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/web-to-markdown/SKILL.mdThe canonical home for this skill is web-to-markdown in bear2u/my-skills
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
This skill fetches and ingests arbitrary public web pages (via WebFetch and optional Playwright) as shown in SKILL.md Step 4 ("WebFetch 도구를 사용하여 웹페이지를 가져오고...") and in AI_OPTIMIZATION.md / EXAMPLES.md (multiple public URLs like https://react.dev/...), then the agent parses and uses that extracted content as structured context for AI/RAG workflows and to decide follow-up actions (e.g., whether to run Playwright), so untrusted third-party content can materially influence tool use and agent behavior.
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 fetches arbitrary webpages at runtime and injects their content into the model prompt/processing flow (e.g., https://react.dev/reference/react/useState is fetched and its HTML/markdown is fed into the WebFetch/Playwright → prompt pipeline), so external content can directly control the agent's prompts and behavior.
- Repository
- bear2u/my-skills
- Commit
1be5394
- 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.