Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent construction data-analysis helper, but users should treat its bundled connector code as demo/sample data rather than verified live open-data integration.
Install only if you are comfortable giving the skill filesystem access to user-supplied project files and potential network access for open-data lookups. Treat the included Python as illustrative/demo code unless you replace or verify the connectors against real data sources, and avoid relying on its sample price, labor, permit, or weather values for business decisions without independent validation.
The skill advertises integration of multiple open external datasets, but most connectors return hard-coded or simulated values. This is a software integrity issue: consumers may believe outputs are current external data when they are actually static placeholders, leading to incorrect analysis, reporting, or business decisions.
The markdown describes integrating data from sources including weather services, and the examples show supplying latitude, longitude, and project date ranges for enrichment and risk assessment. There is no visible warning that using the skill may disclose project-related location and timeline data to third-party services, which is a privacy-relevant behavior for markdown files.
The weather connector is presented as API-backed, but the implementation fabricates records instead of retrieving real source data. This can mislead downstream users into making planning or risk decisions based on false environmental inputs, undermining integrity and trust in the skill’s outputs.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def __init__(self, api_key: Optional[str] = None):
self.api_key = api_key
self.base_url = "https://api.openweathermap.org/data/2.5"
def fetch(
self,
The manifest description is generic and does not define clear activation boundaries, increasing the chance the skill is invoked in situations beyond its intended scope. For a skill with both filesystem and network permissions, ambiguous triggering raises the risk of unnecessary access to local data and external transmission during unrelated tasks.
The skill requests both filesystem and network permissions without any visible disclosure of what local data may be read or what information may be sent externally. This combination is especially risky because it enables a path for collecting local files and transmitting their contents to remote services under a broadly described data-integration purpose.
The book reference presents a Russian title alongside English content, but the skill does not explain any language or locale expectation for users. Because the policy requires avoiding forced language/locale constraints without opt-in or justification, this mixed-language reference should be clarified.
No suspicious patterns detected.