grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill configuration and instructions do not contain any malicious patterns, obfuscation, or dangerous commands. The content is restricted to natural language interaction guidelines.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to intake user plans or designs for critique, which represents a data ingestion surface. However, the skill lacks any capabilities that could be exploited via injection.
- Ingestion points: User-provided plan or design content described in SKILL.md.
- Boundary markers: None defined.
- Capability inventory: None; no tool calls, file writes, network operations, or shell commands are present in SKILL.md or agents/openai.yaml.
- Sanitization: None defined.
Audit Metadata