Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` - Complete documentation (this file)
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple volunteer-tourism ethics helper with no evidence of hidden access, persistence, network use, or destructive behavior.
Before installing, treat this as an informational checklist generator rather than an authoritative source. Verify organizations, fees, child-protection policies, and travel safety information with official or primary sources.
Referenced artifact was not completely inspected
- `SKILL.md` - Complete documentation (this file)
Without declared permissions the skill's intent is opaque and cannot be validated.
The trigger phrases are broad and ambiguous, such as generic references to 'community' or 'evaluation considerations,' which can cause the skill to activate for unrelated travel or general-help requests. Over-broad activation can misroute user input, override more appropriate skills, and create prompt-scope confusion that weakens system control boundaries.
The primary trigger examples are written broadly enough to overlap with ordinary requests for planning help, increasing the chance this skill is selected outside its intended niche. In agent systems, that can degrade routing integrity and lead to irrelevant or misleading guidance being injected into benign travel-planning conversations.
The non-functional requirement 'English documentation primary' imposes a language preference, while the file also includes a Chinese usage scenario, suggesting multilingual use is possible. This can conflict with language/locale neutrality unless the language constraint is optional or explicitly justified.
The manifest sets the skill language to "en", which can indicate a fixed language constraint. Under the policy, locale or language restrictions should either offer user choice or be clearly justified; this file provides neither.