plan-review
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, remote dependencies, or suspicious commands. It is entirely composed of natural language instructions for the agent to act as a technical reviewer.
- [PROMPT_INJECTION]: The instructions are focused on software quality and do not contain patterns intended to bypass AI safety guardrails or override system prompts.
- [DATA_EXFILTRATION]: There are no commands that would lead to the exposure of sensitive credentials or the exfiltration of data to external servers.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and analyze external data (development plans), which is an inherent surface for indirect prompt injection, it does not include instructions that would exacerbate this risk, such as executing untrusted code or ignoring input boundaries.
Audit Metadata