lg-pptx

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill's instructions in SKILL.md and README.md are strictly focused on presentation generation and do not contain patterns designed to override agent safety or bypass filters.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive credentials were found in any of the skill's files.
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides links for manual font installation by the user but does not contain logic for automated remote downloads during script execution.
  • [REMOTE_CODE_EXECUTION]: The builder script does not use eval(), exec(), or any other method to fetch and run remote code.
  • [COMMAND_EXECUTION]: There is no usage of the subprocess module or os.system() to execute shell commands within the Python scripts.
  • [DATA_EXFILTRATION]: The skill does not perform any network operations and has no mechanism to transmit user data to external domains.
  • [SAFE]: The skill implements a legitimate utility for document creation using established open-source libraries and adheres to its stated purpose without performing suspicious activities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:03 PM