spec-kit-implement
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on external project files to define its execution flow, creating a surface where malicious instructions could be embedded in data.
- Ingestion points: Loads
tasks.md,plan.md, andspec.mdfrom thespecs/changes/<name>/directory (SKILL.md). - Boundary markers: Absent; the instructions do not include delimiters or warnings to treat the content of these files as untrusted data.
- Capability inventory: The skill has the capability to write source code, create tests, and modify documentation files within the project structure.
- Sanitization: None; the agent is instructed to directly execute the tasks as defined in the loaded markdown files.
Audit Metadata