alphagbm-macro-view
Track the macro variables that actually move your portfolio — VIX, US10Y, DXY, gold, oil, etc. — with auto-computed impact on user's holdings. Each tracked indicator returns current value, change, and AI-generated impact analysis linked to the user's profiles. Use when: adding a macro indicator, pulling current macro dashboard, asking how VIX affects the portfolio. Triggers on: "track VIX", "current 10-year yield", "how's the dollar doing", "add gold to my macro watch", "remove US10Y", "宏观指标", "美债利率", "美元指数", "VIX恐慌指数".
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The AlphaGBM Macro View skill ingests user free text (e.g., “Track VIX…”, “what’s the macro picture?”, “Is high VIX hurting my positions?”) to decide which internal endpoints/fields to call (POST/DELETE/GET /api/research/macro and then read impact_analysis), meaning outsider-authored text can influence the workflow at runtime.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill requires contacting the runtime API at https://alphagbm.zeabur.app to fetch AI-generated "impact_analysis" text (e.g., via GET /api/research/macro), and that fetched content is presented/used by the agent to drive its responses, so the external URL directly controls agent output.
- Repository
- AlphaGBM/skills
- Commit
6ecea74
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.