Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed city-map editing skill with expected local file edits and optional network sharing/geocoding, with no hidden persistence or deceptive behavior found.
Install only if you are comfortable with a Node.js CLI that edits files in your working directory and may contact mapping/sharing services when those commands are used. Treat `share --short` as uploading the city snapshot, use `--gallery` only for maps you want publicly listed, and consider pinning Playwright if you need reproducible optional screenshot/simulation setup.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
context_enlargeIn = Math.pow(2, context_numBits);
context_numBits++;
}
delete context_dictionaryToCreate[context_w];
} else {
value = context_dictionary[context_w];
for (i=0 ; i<context_numBits ; i++) {
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
context_enlargeIn = Math.pow(2, context_numBits);
context_numBits++;
}
delete context_dictionaryToCreate[context_w];
} else {
value = context_dictionary[context_w];
for (i=0 ; i<context_numBits ; i++) {
The skill documents use of environment variables such as BAIDU_MAP_AK, POWPOWCITY_API_BASE, and POWPOWCITY_ANON_KEY, but it does not declare an explicit tool scope or permissions boundary. In an agent setting, undeclared environment access can cause overbroad secret exposure or make the agent use sensitive host configuration without clear authorization.
The main skill instructions and trigger guidance are written entirely in Chinese, including the directive about when to use the skill. This creates a language/locale constraint in the skill’s natural-language interface without documenting user choice or a justified region-specific limitation.
The instructions tell users to run 'npx playwright' without pinning a specific version. This creates a supply-chain risk because the resolved package version can change over time, potentially introducing malicious or incompatible code during installation.
This line again directs use of 'npx playwright' without a pinned version, exposing the same package-resolution and supply-chain risk. Repeated unpinned install guidance increases the chance that agents or users will execute non-reproducible dependency installation from the network.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import { pathToFileURL } from 'node:url';
const GEOCODE_URL = 'https://api.map.baidu.com/geocoding/v3/';
const PI = Math.PI;
const X_PI = (PI * 3000.0) / 180.0;
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The money formatter hard-codes 'en-US', which forces US-style number formatting in user-visible output regardless of the user's locale or preferences. This is a natural-language/locale policy concern because the tool does not offer any opt-in or configuration for alternative locales.
The Nominatim request hard-codes Accept-Language: 'en', which forces a specific language for results regardless of user preference or environment. This is a natural-language policy concern because the skill does not offer any language choice or document a justified locale restriction.
The file formats currency and population/job counts using toLocaleString('en-US'), which forces a specific locale in user-visible output. The policy allows locale constraints only when users are given a choice or when the restriction is clearly documented and justified, neither of which appears here.
Detected: suspicious.env_credential_access