destination-trip-planning
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill recommends using the
curlcommand-line utility as a fallback mechanism for retrieving raw HTML from websites that block standard browser-based extraction tools. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection and command injection. Ingestion points: External travel and attraction websites researched via web tools or
curl(SKILL.md). Boundary markers: Absent; the skill lacks instructions for the agent to isolate or ignore instructions embedded in the retrieved HTML content. Capability inventory: Web browsing tools and the ability to execute shell commands as suggested in the fallback scraping instructions. Sanitization: Absent; the suggestion to usecurl -sL ... <url>does not include requirements for URL sanitization or escaping, which could be exploited if an untrusted URL is processed. - [SAFE]: The core functionality of the skill follows good practices for travel planning, including verifying pricing from multiple sources and prioritizing traveler accessibility and user confirmation.
Audit Metadata