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
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:30 AM