Skills
skills/pingcap/agent-rules/tidbx/Gen Agent Trust Hub

tidbx

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [Unverifiable Dependencies & Remote Code Execution] (CRITICAL): The skill instructs the agent to perform piped remote script execution from an untrusted source. Evidence: curl https://raw.githubusercontent.com/tidbcloud/tidbcloud-cli/main/install.sh | sh in SKILL.md. This pattern allows immediate, unverified execution of arbitrary code from a third-party repository (tidbcloud/tidbcloud-cli) not included in the Trusted External Sources list.
  • [Indirect Prompt Injection] (HIGH): The skill is vulnerable to instructions embedded in external data.
  • Ingestion points: Remote data from ticloud serverless list and ticloud project list (File: SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Includes resource deletion (ticloud serverless delete) and creation (ticloud serverless create) as defined in SKILL.md and references/ticloud.md.
  • Sanitization: No evidence of input validation or escaping for resource names returned by the API.
  • [Data Exposure & Exfiltration] (LOW): The skill recommends using the --insecure-storage flag for authentication (ticloud auth login --insecure-storage in SKILL.md), which may result in credentials being stored in an unprotected format on the local filesystem.
Recommendations
  • CRITICAL: Downloads and executes remote code from untrusted source(s): https://raw.githubusercontent.com/tidbcloud/tidbcloud-cli/main/install.sh - DO NOT USE
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 05:06 AM