israeli-restaurant-ops
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves processing external, untrusted data in the form of customer reviews to generate response drafts (Step 3).
- Ingestion points: Customer review text provided by the user in SKILL.md and SKILL_HE.md.
- Boundary markers: Absent; the instructions do not use delimiters or provide specific guidance to the agent to ignore or isolate instructions embedded within the review text.
- Capability inventory: None; the skill is comprised of documentation and metadata without any executable scripts or requested tool permissions, which significantly limits the potential impact of an injection attack.
- Sanitization: Absent; there is no mention of filtering, escaping, or validating the input review text.
- [NO_CODE]: The skill is purely informational and instructional, containing only Markdown files and JSON metadata. No executable code files (e.g., .py, .js, .sh) are included in the skill package.
Audit Metadata