skills/cklxx/elephant.ai/ppt-deck/Gen Agent Trust Hub

ppt-deck

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill logic in run.py is limited to dictionary manipulation and template formatting. It does not contain any calls to risky functions such as eval, exec, or subprocess.run.
  • [PROMPT_INJECTION]: While the skill accepts user-provided topics and subtitles, these are treated as data fields within a structured output. The static prompt template (outline_prompt) does not provide a mechanism for user input to override system instructions or bypass security filters.
  • [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It relies on local imports and standard Python libraries for its core functionality.
  • [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were detected. The script only outputs data to standard output via the skill runner utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:30 PM