firewall-review
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external configuration files which represents a potential surface for indirect prompt injection attacks.
- Ingestion points: The Discovery step in SKILL.md identifies numerous file patterns to be read using Read, Grep, and Glob tools.
- Boundary markers: The skill contains a 'Prompt Injection Safety Notice' explicitly instructing the agent to ignore instructions found in configuration comments.
- Capability inventory: The skill utilizes Read, Grep, and Glob tools; it does not request high-privilege tools like file-write or shell execution.
- Sanitization: Instructions specify that configuration content should be treated as untrusted data and not as commands.
Audit Metadata