rug-detection-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate security analysis instructions and templates for evaluating cryptocurrency tokens. All identified behaviors align with the stated purpose of scam detection and investor protection.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze untrusted external data, such as token metadata, website content, and social media feeds, which creates an attack surface for indirect prompt injection. This is an inherent risk of the skill's primary function (auditing external entities) and does not indicate malicious intent in the skill itself.
- Ingestion points: Blockchain RPC data, external websites, and social media platforms (Workflow steps 1, 7, and 8).
- Boundary markers: The skill does not provide specific delimiters or 'ignore' instructions for the external content it processes.
- Capability inventory: The skill utilizes blockchain RPC queries (e.g., getParsedAccountInfo) and general data analysis; it does not contain file-write or unauthorized network-send capabilities.
- Sanitization: No explicit sanitization or filtering logic is provided for the external data ingested during the audit process.
Audit Metadata