cardano-staking
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by processing data from an external blockchain source. 1. Ingestion points: Wallet and pool data are retrieved via the get_stake_delegation tool. 2. Boundary markers: Absent; there are no delimiters specified for the data returned by the tool. 3. Capability inventory: The agent is restricted to Read, Glob, and Grep tools as defined in the skill metadata. 4. Sanitization: Absent; the skill does not specify any validation or sanitization for the retrieved data.
- [CREDENTIALS_UNSAFE]: The skill requires the SEED_PHRASE environment variable. This is a highly sensitive credential necessary for the skill's primary function of accessing Cardano wallet information. This requirement is disclosed in the skill metadata.
Audit Metadata