gog-tasks
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected within the skill files.
- [COMMAND_EXECUTION]: The skill utilizes the gog CLI tool to perform task-related operations. These operations are limited to the intended functionality of managing Google Tasks.
- [PROMPT_INJECTION]: There are no instructions that attempt to bypass AI safety guidelines or override the agent's core behavior.
- [SAFE]: Regarding potential indirect prompt injection: Ingestion points occur where task data is retrieved from Google (e.g., gog tasks list in SKILL.md). Boundary markers are explicitly addressed by the recommendation to use the --wrap-untrusted flag. The capability inventory is limited to Google Tasks CRUD operations via the gog tool. Sanitization is encouraged through the use of safety-oriented CLI flags documented in the skill.
Audit Metadata