agent-cli-hint-completion
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of various CLI tools (such as Playwright, Claude, and Gemini) through its own wrapper command 'agtm run'. This is a primary function of the skill for management and automation.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the '@aiagenta2z/agtm' package from the NPM registry and fetches updated command hints and configurations from the vendor's GitHub repository.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data and executing commands based on that data.
- Ingestion points: External data is ingested from URLs visited via integrated browser tools (like Playwright) and from user-supplied prompts for various third-party LLM CLIs.
- Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying malicious commands embedded in processed external content.
- Capability inventory: The skill possesses capabilities to execute subprocesses, perform network operations, and interact with the file system via the integrated tools it manages.
- Sanitization: There is no description of data sanitization, validation, or filtering of the content retrieved from external sources before it is processed by the agent.
Audit Metadata