lcs-task-slicer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-related documents (PRD, SRS) which are untrusted inputs that could contain malicious instructions designed to influence the agent during the task generation phase.
- Ingestion points: The skill reads project documentation including
prd-enhanced.md,prd.md,srs.md,tests.md,api.md,db.md, andtraceability.md. - Boundary markers: A mandatory review step ('Quiz/Confirm with the user') is included, requiring human approval of the proposed task breakdown before any files are written.
- Capability inventory: The skill is capable of writing multiple markdown files to the local file system within the
.lcs/directory structure. - Sanitization: While no specific content sanitization is described, the skill refers to a 'Shared Coding Workflow Contract' and 'Artifact Writing Safety' rules for execution safety.
Audit Metadata