waf-rule-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where untrusted data is processed by an agent with significant capabilities.
- Ingestion points: Processes user requests and patterns regarding WAF rule creation and security configurations (SKILL.md).
- Boundary markers: Absent; there are no instructions to the agent to delimit or ignore instructions that may be embedded within user-provided patterns.
- Capability inventory: The skill environment is configured with access to shell commands and file writing tools (SKILL.md frontmatter).
- Sanitization: Absent; no explicit validation, filtering, or escaping of user-provided security data is defined.
Audit Metadata