triz
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute a local Python module using a shell command:
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/src" python3 -m tome.channels.triz analyze --topic "<topic>" --domain <domain>. This executes code within the agent's environment using arguments derived from user interaction. - [INDIRECT_PROMPT_INJECTION]: The shell command pattern interpolates user-controlled data (
<topic>and<domain>) directly into the command line. - Ingestion points: The agent takes a topic and a domain from the user and places them into the shell command.
- Boundary markers: While the
<topic>parameter is shown wrapped in double quotes in the example, the<domain>parameter is unquoted, and there are no instructions to sanitize these inputs against shell metacharacters like;,&,|, or backticks. - Capability inventory: The skill possesses the capability to execute shell commands via
python3. - Sanitization: The skill lacks explicit sanitization or validation steps to ensure that user-provided strings do not contain malicious shell commands.
Audit Metadata