get-prediction-markets
Retrieve active prediction-market contracts (Polymarket) with live yes-price probabilities, volume, and close dates, filterable by category or keyword. Use when the user asks what the market odds are on a geopolitical, economic, or election outcome.
75
93%
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
2 findings: 2 high severity. 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 explicitly requires callers to send an API key in the X-WorldMonitor-Key header and includes a literal-looking API key in the documentation, which encourages the LLM to include secret values verbatim in requests or examples (high exfiltration risk).
W008: Secret detected in skill content (API keys, tokens, passwords).
What this means
Detected sensitive credentials directly embedded within the skill content, such as API keys, access tokens, private keys, or service-specific secrets. Secrets should never be hardcoded in plain text within skill instructions.
Why it was flagged
Line 10 contains a literal, high-entropy-looking API key: "wm_0123456789abcdef0123456789abcdef01234567". This is not an obvious placeholder like "YOUR_API_KEY" or "sk-xxxx" and appears to be a real-format credential embedded directly in the documentation, so it meets the definition of a secret to flag. No other values in the file meet the high-entropy secret criteria (the curl example uses an env var $WM_API_KEY, which is an environment placeholder).
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
Yes—at runtime the required workflow calls a public HTTP endpoint and ingests the JSON response fields like `title` (free-form text originating from external prediction-market sources), which is then placed into the agent’s LLM context; while it’s “data not instructions,” it’s still outsider-authored text.
- Repository
- koala73/worldmonitor
- Commit
23ab7d1
- 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.