specs-kit-technical-plan
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests functional specifications and project notes from the local file system to guide the technical planning process. Ingestion points: Processes files such as functional specifications and brainstorming notes located in the docs/specs/ directory. Boundary markers: The skill does not define specific markers to delimit ingested data from agent instructions. Capability inventory: The skill's capabilities are limited to reading local documentation, writing new markdown files, and prompting the user for confirmation via standard interface tools. Sanitization: Ingested content is interpreted for technical context without explicit sanitization routines documented in the skill instructions.
- [SAFE]: The skill's primary operations involve processing project-internal documentation to generate structured technical plans. It includes safeguards such as requiring user confirmation for all architectural decisions and following established project conventions, presenting no evidence of malicious intent or dangerous command execution.
Audit Metadata