create-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as product briefs and conversation history to create and update task documentation.
- Ingestion points: SKILL.md (briefs, PRDs, conversation, repository evidence).
- Boundary markers: No explicit delimiters or warnings are defined to isolate untrusted data from the agent's instructions.
- Capability inventory: The skill specifies the ability to write and update documentation files in docs/tasks/.
- Sanitization: No specific input sanitization or validation logic is provided for the external data.
Audit Metadata