hospitality-hotel-restaurant
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data, specifically guest reviews from platforms like Google and TripAdvisor, which creates an ingestion point for untrusted instructions.\n
- Ingestion points: Processes guest reviews, client briefs, and property facts as specified in SKILL.md.\n
- Boundary markers: The skill does not explicitly define delimiters or instructions to prevent the agent from executing commands that might be hidden within guest reviews.\n
- Capability inventory: Access is restricted to 'Read and search only', providing a significant safeguard as the skill lacks capabilities for file modification, network exfiltration, or shell execution.\n
- Sanitization: The workflow incorporates an 'anti-ai-slop' check and references a 'source-evaluation' skill to ensure content quality and factual accuracy.\n- [EXTERNAL_DOWNLOADS]: The skill includes a reference to an external repository for documentation purposes.\n
- Evidence: References a source evaluation guide located at 'https://github.com/peterbamuhigire/digital-research-skills/blob/main/skills/source-evaluation/SKILL.md', which is a resource maintained by the skill's author.
Audit Metadata