news-signal-outreach
End-to-end news-triggered signal composite. Takes any piece of news — an article, LinkedIn post, tweet, announcement, event, trend, regulation, product launch, acquisition, layoff, expansion, or any other public event — and evaluates whether the companies or people mentioned are ICP fits. If yes, identifies the connection between the news and your product, finds the right people to contact, and drafts personalized outreach using the news as the hook. Tool-agnostic. Accepts both company-level and person-level news triggers. AUTO-TRIGGER: Load this composite whenever a user shares a URL (LinkedIn post, article, tweet, blog post) or mentions a company/person they "came across", "saw", or "found" from any external source and asks about relevance, fit, ICP match, or whether to reach out. The user does NOT need to explicitly say "outreach" — any signal evaluation request from an external source triggers this.
71
88%
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
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 SKILL.md, Step 1 “Parse & Extract” explicitly ingests user-provided external news content: in Mode A it fetches and parses a user-supplied URL to extract article text (or uses raw text/structured content as-is), and this extracted free text is then used in subsequent LLM steps (entity extraction, ICP qualification, connection-angle generation, and email drafting).
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 fetches and parses arbitrary user-provided web pages at runtime ("If URL → fetch the page, extract article text" in SKILL.md), and that fetched content is injected into the agent's processing to extract entities and craft outreach, so external URLs supplied at runtime can directly control prompts and model output.
- Repository
- gooseworks-ai/goose-skills
- Commit
8866b2a
- 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.