task-planning
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security concerns were identified during the analysis of the skill's instructions and templates.
- [NO_CODE]: The skill does not include any scripts, executable binaries, or code modules.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-supplied data for feature planning in SKILL.md. However, it lacks any functional capabilities that could be leveraged maliciously. 1. Ingestion points: User descriptions of software features and tasks entering through the task-planning process. 2. Boundary markers: Absent; the skill relies on standard LLM completion of markdown templates. 3. Capability inventory: None; the skill does not perform any file-system, network, or subprocess operations. 4. Sanitization: Absent; the skill does not filter or escape user-provided feature descriptions.
Audit Metadata