nansen-dca-watch
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from the Nansen platform (e.g., token symbols, labels, and flow intelligence), which are externally controlled. This presents a surface for indirect prompt injection if an attacker poisons the blockchain metadata retrieved by the CLI.
- Ingestion points: Output from
nansen researchcommands. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: Data retrieval and display via the Nansen CLI.
- Sanitization: No sanitization or validation of the retrieved blockchain data is specified.
- [NO_CODE]: The skill consists of documentation and command-line examples in
SKILL.mdbut does not include any executable scripts or binary files.
Audit Metadata