codearts-build

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of external data without explicit sanitization or boundary markers.
  • Ingestion points: Data enters the agent context through the outputs of codearts-cli build list and codearts-cli build status in SKILL.md.
  • Boundary markers: Absent. There are no instructions or delimiters used to warn the agent that retrieved job names, descriptions, or status logs should be treated as untrusted data.
  • Capability inventory: The skill has the capability to execute shell commands via the codearts-cli binary as defined in SKILL.md.
  • Sanitization: None. The skill does not implement any validation or filtering of the strings returned by the CLI tool before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 08:05 AM
Security Audit — agent-trust-hub — codearts-build