plaza-one

clawhub:plaza-one

View source
C
55/100

First Seen

Feb 20, 2026

Last Scanned

Feb 22, 2026

Findings

3

Score

55/100

HIGH 3

Findings (3)

HIGH
Autonomous agent spawning
L26

Detects autonomous sub-agent or cron-based execution without human oversight

spawn sub-agent + autonomous
FIX

Remove directives that force the agent to call specific tools or APIs not required for the skill's stated functionality. Tool calls should be determined by user intent, not embedded directives.

FP?

Likely FP if the skill legitimately needs to call other tools as part of its workflow (e.g., a deployment skill that calls git and cloud CLI tools).

HIGH
Data transmission pattern
L53

Detects patterns indicating sensitive data being sent to external services

send credentials to
FIX

Restrict file reading to the project directory and block outbound network calls that include file contents. Implement file path validation to prevent directory traversal.

FP?

Likely FP if the tool legitimately reads project files and displays them to the user locally, without sending data to external services.

HIGH
Shell metacharacters in MCP config args
L65

Detects shell metacharacters (pipes, backticks, subshells) in MCP server command arguments

"command": "observe" }`
FIX

Remove credentials (API keys, tokens, passwords) from MCP server configuration. Use environment variable references (e.g., ${API_KEY}) or a secrets manager instead of inline values.

FP?

Likely FP if the credential value is a placeholder (e.g., your-api-key-here, sk_test_xxx) in example configuration.