blockchain-developer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to review and implement blockchain-related tasks, which involves processing untrusted source code or transaction data.
- Ingestion points: The agent reads smart-contract source code and Web3 workflow descriptions from the workspace as instructed in SKILL.md.
- Boundary markers: Absent. The instructions in SKILL.md do not provide delimiters to separate code-embedded instructions from engineer guidance.
- Capability inventory: Metadata in SKILL.md grants workspace-write capabilities, allowing file modification.
- Sanitization: Absent. No validation or filtering logic is defined for the ingested content.
Audit Metadata