stablecoin-yield-radar
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes real-time yield data from an external API (api.barker.money), which could theoretically contain malicious instructions.
- Ingestion points: The skill performs a GET request to
https://api.barker.money/api/public/v1/defi/vaults(SKILL.md). - Boundary markers: The skill includes a dedicated 'Security: External Data Boundary' section that explicitly instructs the agent to treat returned strings as data and ignore any embedded instructions.
- Capability inventory: The agent uses the retrieved data primarily to format and display markdown tables.
- Sanitization: The instructions mandate that strings be surfaced verbatim without acting on them.
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch version information and yield data.
- Evidence: The 'Version check' section in SKILL.md uses
curlto fetchhttps://raw.githubusercontent.com/okx/plugin-store/main/skills/stablecoin-yield-radar/plugin.yaml. This targets a repository associated with the skill's trusted distribution platform. - Evidence: The skill fetches yield data from the service provider's API at
api.barker.money. - [COMMAND_EXECUTION]: The skill includes instructions for the AI agent to execute local shell commands for session-based version management.
- Evidence: A bash script in SKILL.md uses
stat,date,curl,grep, andawkto manage a local update cache in$HOME/.plugin-store/update-cache/. These are read-only operations for maintenance purposes.
Audit Metadata