Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
AutoCount
v1.0.0Create and validate AutoCount business documents through AutoCount Web API. Use when the user wants to create or test sales invoices, purchase invoices, good...
⭐ 0· 62·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md clearly targets AutoCount Web API endpoints and the described endpoints and payloads are consistent with the stated purpose. However, the skill metadata lists no required credentials or primaryEnv while the instructions explicitly require an API name and API key (X-API-NAME and X-API-KEY). That discrepancy is incoherent with how an API integration normally declares required credentials.
Instruction Scope
Runtime instructions are narrowly focused on building and submitting AutoCount document payloads and then fetching created records. They do not instruct reading arbitrary local files or other unrelated credentials. One operational issue: examples and the referenced test notes use HTTP on port 9999 (no TLS), meaning API keys would be sent in cleartext if the base URL is not secured — a network security concern but not scope creep.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk or downloaded during install — low install risk.
Credentials
The SKILL.md requires API credentials (X-API-NAME and X-API-KEY) to operate but the registry metadata lists no required environment variables or primary credential. That mismatch means the skill might prompt the user for secrets at runtime or rely on ad-hoc input rather than declaring them up-front, which reduces transparency. The examples also imply use of HTTP (insecure) which exacerbates the risk of credential exposure.
Persistence & Privilege
The skill does not request always:true, has no install steps, and does not ask to modify other skills or system settings. It appears to run only when invoked, which is appropriate for its purpose.
What to consider before installing
This skill appears to be what it says — a helper for talking to an AutoCount Web API — but there are two practical concerns you should resolve before installing or using it: (1) the SKILL.md requires an API name and API key (X-API-NAME and X-API-KEY) but the skill metadata does not declare any required credentials. Ask the publisher why required credentials are not declared and whether the skill will request/store them. (2) Example traffic uses plain HTTP on port 9999; if you point this skill at a remote or untrusted host your API keys and document data could be sent in cleartext. Only use it against endpoints you control or that support HTTPS. If the publisher can update metadata to list the required env vars (or explain why they are omitted) and confirm TLS support, this would reduce the concern. Also verify you trust the endpoint and that the agent will not be asked to transmit unrelated secrets or sensitive files.Like a lobster shell, security has layers — review code before you run it.
latestvk97ft5jw8tf96vx7k21r77hh2584nz7y
License
MIT-0
Free to use, modify, and redistribute. No attribution required.