account-admin
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a shell function
api()that interfaces with a local utility scriptapi-request.shto perform API operations. This is a standard architectural pattern for AI agent skills. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Spotify Ads API (SKILL.md), which constitutes an external data surface. The skill mitigates risks by enforcing a protocol in SKILL.md that requires the agent to resolve IDs, present a plan, and obtain explicit user confirmation before executing mutation commands (POST, PATCH, DELETE).
- [SAFE]: The instructions include specific guardrails for handling sensitive PII and financial metadata such as emails, tax IDs, and billing data in SKILL.md, directing the agent to treat them as sensitive and minimize their display.
Audit Metadata