gsdl-create-spec
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the local filesystem, specifically targeting a dedicated .planning directory for reading and writing files. It does not perform network operations or execute arbitrary system commands.
- [PROMPT_INJECTION]: The skill ingests data from .planning/[project-name]/seed.md, which represents a surface for indirect prompt injection.
- Ingestion points: Reading seed.md from disk (SKILL.md).
- Boundary markers: None identified; content is used directly for requirement analysis.
- Capability inventory: The skill is limited to text processing and file storage; no network, shell, or code execution capabilities are present.
- Sanitization: None; the skill relies on model guardrails to handle content from the seed file.
Audit Metadata