travel-planner
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external web searches to create travel plans, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Web search results retrieved during the destination research phase as described in Step 4 of the workflow.\n
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within search results.\n
- Capability inventory: The associated Python scripts (
travel_db.py,plan_generator.py) are restricted to local file operations within the skill's data directory (~/.claude/travel_planner/) and do not possess network or elevated command execution capabilities.\n - Sanitization: No explicit sanitization or validation of external search content is performed before processing.
Audit Metadata