track-tasks
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external issue trackers which may contain malicious instructions.
- Ingestion points: Reads task data and tracking configuration from .agents/task-tracker.md and remote platforms (GitHub, GitLab, Linear) via CLI tools.
- Boundary markers: The skill employs task templates but does not implement explicit delimiters or 'ignore' instructions to prevent the execution of instructions embedded in ingested task bodies or comments.
- Capability inventory: The skill has permissions to read, create, and delete files and directories within the .agents/tasks/ path and can invoke the gh and glab CLI utilities.
- Sanitization: No sanitization or validation of content retrieved from remote trackers is mentioned before the data is processed or output.
- [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub) and glab (GitLab) CLI tools to perform synchronization operations. These tools are used for their intended administrative purposes and rely on authenticated user sessions.
Audit Metadata