crypto-research-desk
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown for synthesizing market data. No malicious code, obfuscation, or sensitive data access patterns were identified.
- [PROMPT_INJECTION]: Analysis of indirect prompt injection surface: (1) Ingestion points: The skill processes external 'gather-seat' data sources as mentioned in SKILL.md. (2) Boundary markers: The instructions lack specific delimiters to isolate untrusted data from instructions. (3) Capability inventory: No dangerous tools (shell, network, or file system access) are defined or requested in the frontmatter or instructions. (4) Sanitization: There are no filters or sanitization steps provided for incoming data. The risk is considered negligible due to the absence of executable tools or privileged operations.
Audit Metadata