crypto-listings
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection because it instructs the agent to browse and process content from external third-party websites.
- Ingestion points: Data is ingested from external URLs including official exchange announcement pages, CoinGecko market pages, and CoinMarketCap listing pages as specified in
SKILL.md. - Boundary markers: The instructions do not provide explicit delimiters or guidance to the agent to disregard instructions that might be embedded in the retrieved web content.
- Capability inventory: The skill's capabilities are limited to browsing and markdown report generation. No scripts, file-system writes, or subprocess executions are defined within the skill package.
- Sanitization: There is no mention of sanitizing or validating the integrity of the external data before it is presented to the agent for summarization.
- [NO_CODE]: The skill package (
crypto-listings.skill) and its source files (SKILL.md,README.md) contain only markdown instructions and configuration. No executable scripts, binary payloads, or persistence mechanisms were detected, reducing the overall threat profile.
Audit Metadata