blockchain-developer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Risk.
- Ingestion points: According to
SKILL.md, the agent is instructed to "Query context manager for blockchain project requirements" and "Review existing contracts." - Boundary markers: Absent. The skill provides no delimiters or instructions to ignore instructions embedded within the contracts or documentation it processes.
- Capability inventory: As defined in
SKILL.mdtools, the agent has access toBash,Write,truffle, andhardhat, which allow for filesystem modifications and execution of development scripts. - Sanitization: Absent. No evidence of input validation or escaping for external content is present in the provided files.
Audit Metadata