simready-foundation-add-feature
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection by incorporating user-supplied data into generated project files.
- Ingestion points: The workflow collects user inputs like
display_name,feature_id, andruntime_promiseto populate new files. - Boundary markers: There are no specified delimiters or 'ignore' instructions to isolate user-supplied strings within the generated Markdown and JSON artifacts.
- Capability inventory: The skill is authorized to write and update files in the
nv_core/sr_specs/docs/features/andskills/directories. - Sanitization: No explicit sanitization or validation logic for user-provided text is defined in the instructions.
- [REMOTE_CODE_EXECUTION]: The skill automates the creation of new AI agent skill definitions (
SKILL.mdfiles), which is a form of local template-based code generation. - Evidence: Instruction 8 directs the agent to generate a conform skill file at
skills/simready-foundation-conform-fet-###-<feature-name>/SKILL.md.
Audit Metadata