diagnosing-team-skills

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run several shell commands including cat, command -v, bash, and pytest. These are used for diagnosing the local environment state.
  • [EXTERNAL_DOWNLOADS]: Includes a reference to the vendor's GitHub repository (github.com/tikalk/adlc-cli) for technical documentation and boundaries.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific configuration files (.adlc/init-options.json) to verify system state. While this represents a data ingestion surface, it is constrained to local configuration within a diagnostic context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:32 PM