skills/curiositech/some_claude_skills/event-detection-temporal-intelligence-expert/Gen Agent Trust Hub
event-detection-temporal-intelligence-expert
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external location APIs and photo metadata, creating a vulnerability where malicious data could influence agent behavior.
- Ingestion points: The PlaceRecognizer class in references/place-recognition-life-events.md fetches address and semantic place data from external geocoding services. The EventDetectionPipeline in references/temporal-diversity-pipeline.md ingests photo metadata and visual content signals.
- Boundary markers: The instructions and implementation scripts lack explicit delimiters or 'ignore embedded instructions' warnings for data received from external sources.
- Capability inventory: The skill utilizes powerful tools including Bash, Write, Edit, and WebFetch, which could be leveraged if an injection is successful.
- Sanitization: No evidence of escaping, validation, or filtering of location strings or photo metadata is present in the implementation references.
Audit Metadata