isr-tables-figures
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational, providing directives for an AI agent to follow when assisting with manuscript preparation. No security threats across the 11 categories were detected.
- [COMMAND_EXECUTION]: While the text mentions tools like
etableorplot_from_result, these are references to expected environment capabilities (likely Stata or MCP tools) rather than shell commands executed by the skill itself. - [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external manuscript data. This represents a standard functional surface for an AI agent and does not introduce specific vulnerabilities beyond the inherent behavior of large language models.
Audit Metadata