web-research
Neural web search and content extraction using x402-protected APIs. Better than WebSearch for deep research and WebFetch for blocked sites. USE FOR: - Deep web research and investigation - Finding similar pages to a reference URL - Extracting clean text from web pages - Scraping sites that block standard fetchers - Getting direct answers to factual questions - Research requiring multiple sources - Crawling multiple pages from a website TRIGGERS: - "research", "investigate", "deep dive", "find sources" - "similar to", "pages like", "more like this" - "scrape", "extract content from", "get the text from" - "blocked site", "can't access", "paywall" - "what is", "explain", "answer this" - "crawl", "crawl site", "scrape entire site" Use `npx agentcash@latest fetch` for stableenrich.dev endpoints. Prefer Exa for semantic/neural search, Firecrawl for direct scraping.
68
85%
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 workflow returns a JWT token and instructs the agent/user to insert that token verbatim into subsequent poll requests (via the query string), which requires the LLM to handle and emit 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 skill’s required runtime workflow (e.g., “Deep Research” and “Blocked Site Scraping”) uses Exa search/find-similar followed by Exa contents and Firecrawl scrape/search, which ingests outsider-authored web page text chosen based on attacker-controlled free-text queries/URLs.
- Repository
- Merit-Systems/agentcash-skills
- Commit
3d657b7
- 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.