Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed social media analytics skill with optional social API credentials, and the inspected artifacts do not show hidden execution, exfiltration, or destructive behavior.
Install only if you are comfortable providing social-platform credentials to the runtime. Prefer read-only, least-privilege tokens; keep business metrics and generated reports private; use manual CSV mode if you do not want to connect accounts. Treat automatic reporting claims as not implemented by the inspected script.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
description: Twitter API Secret
required: false
LINKEDIN_ACCESS_TOKEN:
description: LinkedIn Access Token
required: false
THREADS_TOKEN:
description: Threads API Token
The skill declares environment-variable requirements for multiple social-platform credentials but does not define any explicit permission or allowed-tools scope. That makes credential and data access boundaries unclear to users and the host platform, increasing the chance the skill can access sensitive secrets or analytics data without sufficiently transparent authorization expectations.
The invocation example "When should I post for maximum engagement?" is a natural-language phrase that could easily occur in ordinary conversation and does not name the skill or narrow the context. The README does not provide exclusion conditions or a constrained activation scope, so this increases the risk of unintended invocation.
The skill requests or relies on social-platform credentials and analyzes potentially sensitive account-performance data, yet it does not present a clear warning about handling tokens, account metadata, competitor analysis data, and generated reports. Users may provide secrets or business-sensitive metrics without understanding the privacy implications or where the data may be processed.
Most of the skill is written in English, but the author-support section switches to Chinese without indicating that multilingual output is optional or user-selected. This can violate language/locale consistency expectations because the file imposes a different language in part of the user-facing documentation without opt-in.
No suspicious patterns detected.