imagegen-scene-ppt

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's components are dedicated to presentation design and automation. The inclusion of a public skill auditor (audit_public_skill.py) demonstrates a security-first design by identifying potential credential leaks and private path exposures in projects. All file operations and logic are consistent with the stated purpose of document generation.\n- [COMMAND_EXECUTION]: Subprocess calls identified in package_image_deck.py and test_semantic_workflow.py are used for legitimate internal functions, such as invoking LibreOffice (soffice) for PDF conversion and executing local test suites. These calls do not ingest unvalidated external input and are not susceptible to command injection in this context.\n- [CREDENTIALS_UNSAFE]: No hardcoded credentials, tokens, or private keys were found. The skill contains regex patterns designed to detect and block the accidental publication of such secrets, serving as a defensive mechanism rather than a threat.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 11:33 AM
Security Audit — agent-trust-hub — imagegen-scene-ppt