attention-reset
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest user-supplied screen-time data, app statistics, and descriptions of habits. While this provides a surface for untrusted data ingestion, the risk is negligible as the skill lacks any tools, scripts, or system access to exploit.
- Ingestion points: Screen-time statistics and behavioral descriptions provided by the user as requested in the 'Required Inputs' section of SKILL.md.
- Boundary markers: None explicitly defined; instructions rely on natural language processing.
- Capability inventory: Zero. The skill does not request any tool permissions or include executable code.
- Sanitization: Not applicable due to lack of capabilities.- [NO_CODE]: The skill consists exclusively of markdown-formatted natural language instructions and YAML metadata. It contains no shell commands, scripts (Python, Node.js), or binary executables.
Audit Metadata