travel-companion
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from social media platforms (TikTok, Instagram) and event sites (Eventbrite), which could contain malicious instructions designed to influence the agent's behavior during processing.
- Ingestion points: Browser snapshots of TikTok, Instagram, Eventbrite, and Google Maps search results as described in SKILL.md and references/browser.md.
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded in the snapshots.
- Capability inventory: The skill can perform network operations via the AgentMail API (references/agentmail.md) and control a browser instance using OpenClaw (SKILL.md).
- Sanitization: There are no explicit sanitization or filtering steps for the text extracted from the snapshots before it is used to compile itineraries.
Audit Metadata