spec-driven-modify
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with the project environment. Evidence: It runs 'ls .spec-driven/' to verify the project is initialized and 'node {{SKILL_DIR}}/scripts/spec-driven.js modify' to manage and list change artifacts.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core function of reading and processing multiple external project files. Ingestion points: The skill reads content from 'proposal.md', 'design.md', 'tasks.md', 'questions.md', '.spec-driven/config.yaml', and various files within the 'specs/' directory. Boundary markers: There are no specific delimiters or instructions used to prevent the agent from following directions embedded within these files. Capability inventory: The skill has the capability to execute shell commands via 'node' and write changes back to the filesystem. Sanitization: No explicit sanitization, validation, or filtering of the ingested file content is performed.
Audit Metadata