chatbot-review
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
composiocommand-line tool through the bash environment to discover and execute toolkit actions. These commands are part of the intended functionality for managing chatbot integrations and do not exhibit malicious behavior. - [PROMPT_INJECTION]: The skill includes an Indirect Prompt Injection surface as it processes external chatbot conversation logs which are considered untrusted data.
- Ingestion points: External conversation logs are retrieved in Step 2 of the workflow.
- Boundary markers: No explicit delimiters or instructions to ignore potential commands within the data are present.
- Capability inventory: The skill utilizes shell execution and the
composioCLI toolset. - Sanitization: There is no evidence of sanitization or filtering applied to the ingested conversation data before analysis.
Audit Metadata