aidlc-tasks

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for project orchestration and task management. It does not perform network operations, execute arbitrary code, or access sensitive system credentials. Its primary functions are reading design documentation and writing implementation plans to local markdown files.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests untrusted data from design documents to generate tasks.
  • Ingestion points: Reads project documentation from context.md, design.md, design/*.md, and testing-strategy.md.
  • Boundary markers: None identified. The skill directly processes the content of these files without specific 'ignore instructions' delimiters.
  • Capability inventory: The skill is limited to file system write operations for planning artifacts such as tasks.md, decisions-tasks.md, and audit.md. It lacks network exfiltration or shell execution capabilities.
  • Sanitization: No validation or sanitization of the content inside ingested markdown files is performed before it influences the generated task list.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 08:00 AM
Security Audit — agent-trust-hub — aidlc-tasks