hospitality-hotel-restaurant
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as client intakes and research engines, which creates a surface for potential indirect prompt injection attacks. However, this functionality is intrinsic to the skill's purpose of business planning.
- Ingestion points: The workflow in
SKILL.mdrequires data from "Client intake", "research engines", and "external publication". - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested data.
- Capability inventory: According to the Capability Contract in
SKILL.md, the skill performs "Read/search, calculation, modelling and document production". - Sanitization: No explicit sanitization or validation logic is defined for the external inputs before they are interpolated into the planning process.
- [SAFE]: The skill references an external accounting doctrine hosted on GitHub (
github.com/peterbamuhigire/chwezi-accounting-doctrine). This is a documented resource provided by the author to support the skill's accounting logic and does not involve executable code or unsafe automated downloads.
Audit Metadata