glam
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it ingests and processes untrusted data from the Solana blockchain and external DeFi protocols to perform sensitive operations.
- Ingestion points: Data is ingested through vault state queries (e.g.,
glam-cli vault viewinSKILL.md) and SDK state model fetching (e.g.,client.vault.fetchinresources/sdk/client.md). - Boundary markers: Absent; the instructions do not implement delimiters or specific warnings to ignore instructions embedded in external data.
- Capability inventory: The skill empowers the agent with high-impact financial capabilities, including executing token swaps (
jupiter swap), lending/borrowing (kamino-lend), and cross-chain USDC bridging (cctp bridge-usdc). - Sanitization: Absent; the agent processes output from CLI tools and SDK calls without explicit sanitization or validation of the content against injection patterns.
Audit Metadata