crypto-market-research
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests cryptocurrency market data from an external API, which could potentially contain instructions intended to influence the agent's behavior.
- Ingestion points: The
scripts/crawlora.shscript fetches data fromapi.crawlora.net. - Boundary markers: There are no explicit instructions or delimiters defined in
SKILL.mdto help the agent distinguish between the fetched data and its own instructions. - Capability inventory: The skill utilizes a shell script that uses
curlto perform network operations. - Sanitization: While the script safely URL-encodes input parameters, the raw JSON content from the API is not filtered or sanitized for potential natural language instructions before being processed by the agent.
Audit Metadata