ppt-agent-workflow
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the instructions or references. The skill follows best practices for guiding agent behavior.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands or scripts. It relies on the installing agent's environment for tool execution without prescribing specific commands.
- [DATA_EXFILTRATION]: No instructions for accessing sensitive files (such as .ssh, .aws, or .env) or exfiltrating data to external servers were found.
- [PROMPT_INJECTION]: The skill uses instructional language to guide the workflow. It does not contain bypass markers, jailbreak attempts, or instructions to ignore safety protocols.
- [REMOTE_CODE_EXECUTION]: There are no remote script downloads or dynamic code execution patterns. The provided prompt templates for SVG and HTML generation are safe templates for the agent to use.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or tokens are present in any of the files.
Audit Metadata