debate-kickoff

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes a local shell script ${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.sh to identify available model providers. This uses an environment variable for the path and is a standard procedure for identifying execution environment capabilities.- [INDIRECT_PROMPT_INJECTION]: Ingests user input to frame a debate motion. The skill transforms user technical questions into a formatted proposition before passing them to the /octo:debate tool. While it lacks explicit delimiters for the user content, the instruction to restate the input as a single proposition serves as a normalization step that mitigates the risk of direct instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 02:45 AM
Security Audit — agent-trust-hub — debate-kickoff