tasklist
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes an import feature that processes untrusted data from external files.
- Ingestion points: Project artifacts such as meeting notes or reports read using the
/as:tasklist importcommand. - Boundary markers: Although a human must confirm every imported task, the instructions do not include markers to tell the agent to ignore potential commands embedded in the imported files during the extraction process.
- Capability inventory: The skill has permissions to Read, Write, and Edit files within the project environment.
- Sanitization: There is no evidence of sanitization applied to the data extracted from external artifacts.
Audit Metadata