nd-setshift
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and metadata. It contains no executable scripts, commands, or network operations. Its behavior is limited to providing tactical advice for debugging and task management.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it instructs the agent to read external files such as
ERRORS.md, debug logs, and session notes. While this could theoretically ingest malicious instructions from compromised logs, it is a low-risk surface essential to the skill's primary function. Ingestion points:ERRORS.md, debug logs, session notes. Boundary markers: None. Capability inventory: None (the skill has no code execution capabilities). Sanitization: None.
Audit Metadata