architect-reviewer-agent
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown documentation and templates. It does not contain any scripts, binaries, or command-line instructions that could pose a security risk.
- [PROMPT_INJECTION]: Analysis of the instructions shows no attempts to bypass safety filters, override system prompts, or implement jailbreak-style behavior.
- [EXTERNAL_DOWNLOADS]: No external URLs, repositories, or remote resources are referenced or downloaded by this skill.
- [DATA_EXFILTRATION]: The skill lacks any mechanism for accessing sensitive local files or transmitting data to external destinations.
- [SAFE]: The skill defines a vulnerability surface for indirect prompt injection as it processes untrusted code changes; however, because it lacks dangerous capabilities (network access, file writing, or command execution), this risk is negligible. Ingestion points: user-provided code changes in SKILL.md. Boundary markers: absent. Capability inventory: none. Sanitization: absent.
Audit Metadata