devils-advocate
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected in the skill's instructions or logic.
- [DATA_EXFILTRATION]: The skill accesses local lecture files and project rules using 'Read', 'Grep', and 'Glob' tools. This access is necessary for its stated pedagogical purpose and is restricted to local file reading with no outbound network operations.
- [PROMPT_INJECTION]: The skill processes external content from lecture files, which represents a surface for indirect prompt injection. However, the risk is minimized because the skill lacks capabilities to execute code, write to the file system, or exfiltrate data.
Audit Metadata