scan-cyber-threats
Retrieve active cyber-threat intelligence — malware IOCs, C2 infrastructure, and CISA known-exploited vulnerabilities — filterable by type, source, and severity. Use when the user asks about current cyber threats, IOCs, or actively exploited CVEs.
76
96%
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 embeds a literal-looking API key (wm_0123456…) and mandates supplying it in the X-WorldMonitor-Key header, which encourages the LLM or users to include secret values verbatim in commands or outputs.
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
The file contains a literal API key in the Authentication example: "X-WorldMonitor-Key: wm_0123456789abcdef0123456789abcdef01234567". This is a long, specific key-like value (prefix "wm_" plus 40 hex chars) rather than a generic placeholder like YOUR_API_KEY or sk-xxxx, so it appears to be a real/usable credential and meets the secret definition. No other high-entropy credentials are present; the curl example uses an environment variable ($WM_API_KEY) which is not a value and is ignored.
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
SKILL.md requires calling `GET https://api.worldmonitor.app/api/cyber/v1/list-cyber-threats` and then placing the returned `threats` text fields (e.g., `tags`, `malwareFamily`, `location`) into the agent context; those fields come from public/community threat feeds with community submissions (outsider-authored content), creating an indirect prompt-injection channel via the LLM-reading of the JSON response.
- 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.