sdd-riper-one-light
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a development workflow framework that mandates task verification, evidence-based completion, and manual approval gates before code modifications occur.
- [COMMAND_EXECUTION]: The skill utilizes a local utility script
scripts/default_prompt_check.pyto inspect and configure project-level agent instruction files. The script is contained within the skill package, uses standard library modules (pathlib, json, re), and performs only local file operations intended for project initialization. - [DATA_EXFILTRATION]: The skill instructions explicitly warn against the exfiltration of sensitive information, specifically forbidding the submission of credentials, private machine paths, or local database traces to the LLM or code repositories.
- [PERSISTENCE]: The skill facilitates the creation of project-specific instruction files (e.g.,
AGENTS.md,.cursorrules) to ensure the agent maintains its operational protocol across multiple chat sessions. This behavior is documented and requires user confirmation before changes are applied.
Audit Metadata