award-sweet-spots
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a local JSON file to generate travel recommendations, creating a potential vector for indirect prompt injection if the source data is manipulated.
- Ingestion points: Instructions specify cross-referencing against
data/sweet-spots.jsonfor rates, devaluation history, and booking windows. - Boundary markers: There are no explicit markers or instructions provided to the agent to treat the content of the JSON file as untrusted data or to ignore any embedded instructions.
- Capability inventory: The skill's functionality is limited to information retrieval, data comparison, and text-based recommendations. It does not include tools for writing files, executing code, or performing network operations.
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the data ingested from the reference file.
Audit Metadata