tasks
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external task management system (e.g., via
ttasks mine,ttasks show,ttasks questions). - Ingestion points: The skill reads task details, packets, and questions from the
ttaskstool output. - Boundary markers: There are no explicit instructions or delimiters defined to isolate task content from the agent's instructions.
- Capability inventory: The skill can execute commands via the
ttasksbinary to update work, assign tasks, and add artifacts. - Sanitization: No sanitization or filtering logic is specified for the content retrieved from the task system.
- [COMMAND_EXECUTION]: The skill uses a shell script wrapper to execute a system binary.
- Evidence: The file
scripts/tasks.shusesexec ttasks "$@"to pass all arguments directly to thettasksbinary. While standard for a wrapper, this allows the agent to execute any functionality supported by that binary.
Audit Metadata