rt-ica
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses instructional language to structure agent reasoning and does not contain any attempts to bypass safety filters or override system constraints. Its logic actually serves to increase the agent's adherence to project constraints.
- [DATA_EXFILTRATION]: No network calls or commands to access sensitive system files (e.g., credentials, SSH keys) are present. The mention of 'secrets' and 'credentials' in the documentation is purely categorical and used as an example for the agent to check for required access.
- [EXTERNAL_DOWNLOADS]: The skill contains references to academic research papers hosted on 'arxiv.org'. These are static informational links and are not used for runtime downloads or code execution.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or scripts included in the skill. The Mermaid diagram and tables are for instructional purposes only.
- [NO_CODE]: The skill consists entirely of Markdown instructions and reasoning logic without any associated executable scripts or binary files.
Audit Metadata