debate-kickoff
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script at
${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.shto verify which model providers are currently available for the debate. - [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied technical questions and transforms them into a 'motion' for a debate tool, creating a vulnerability surface where instructions hidden in the user input could influence the tool's behavior.
- Ingestion points: User's technical decision query (e.g., "Redis or Memcached?") provided at runtime.
- Boundary markers: None present; the motion is formed directly from the user's context.
- Capability inventory: Executes a local shell script (
check-providers.sh) and invokes the/octo:debateplatform command. - Sanitization: No explicit validation or escaping of user input is described before it is formatted into the motion and side assignments.
Audit Metadata