wallet-security
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches resource lists from the author's GitHub repository (gmh5225/awesome-web3-security).
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process content from a remote Markdown file, creating a surface where external content could influence agent behavior.
- Ingestion points: Fetches data from
https://raw.githubusercontent.com/gmh5225/awesome-web3-security/refs/heads/main/README.mdas specified inSKILL.md. - Boundary markers: None present in the instructions.
- Capability inventory: No scripts, command execution, or file system write capabilities were found in the skill.
- Sanitization: No filtering or validation of the remote content is defined.
Audit Metadata