course-content-map
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is designed for local workspace exploration with clear boundaries and safety checks.
- [PROMPT_INJECTION]: The skill proactively addresses indirect prompt injection risks in its Anti-Patterns section, instructing the agent to never treat external content, tool responses, or generated logs as trusted instructions.
- [COMMAND_EXECUTION]: The documentation references a local script (scripts/export-gemini-skill.py) for skill portability. This is an administrative instruction for the user and is not invoked by the agent during the skill's primary workflow.
- [DATA_EXFILTRATION]: The workflow focuses on local file analysis and updating specific memory files within the project. No network-enabled tools or data exfiltration patterns were observed.
Audit Metadata