trace-trade-flows
Retrieve strategic UN Comtrade commodity flows with anomaly flags. Use when the user asks who trades a critical commodity, which flows changed sharply, or how trade exposure is shifting.
72
89%
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 requires callers to send a raw API key in the X-WorldMonitor-Key header (and even includes a literal example key), which means an agent making or generating requests could be required to handle or emit secret API key values verbatim.
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 12 contains a literal API key-style value: "wm_0123456789abcdef0123456789abcdef01234567". This is a high-entropy, specific key-like string (prefix + long hex-like sequence) used as an example header value rather than a placeholder such as "YOUR_API_KEY" or "sk-xxxx". Per the secret definition, this is a hardcoded credential-like value and should be treated as a secret.
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 required runtime workflow calls a public API endpoint that returns upstream-labeled free text fields (e.g., `reporterName`, `partnerName`, `cmdDesc`) from UN Comtrade slices, which can include outsider-authored content that the LLM then ingests for analysis/quoting.
- 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.