birdeye
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes data from the Birdeye API that originates from public blockchain state, such as token names, symbols, and metadata. Because these fields can be set by any user creating a token, they represent an attack surface for indirect prompt injection where malicious instructions could be embedded to influence the agent's responses.
- Ingestion points: API response payloads processed in
templates/birdeye-client.tsand illustrated inSKILL.mdusage examples. - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions found within token data.
- Capability inventory: Read access to real-time market data, token fundamentals, and wallet transaction history via the Birdeye API.
- Sanitization: Absent; the implementation relies on standard JSON parsing and does not apply filters or sanitization to string fields derived from token metadata.
Audit Metadata