@1977/billions-faiar
Fail
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
npx clawhub@latestto execute code from a remote npm package. This allows for arbitrary remote code execution, as the package's behavior is not defined or constrained within the skill files. - [EXTERNAL_DOWNLOADS]: The skill fetches content from the npm registry via the
clawhubpackage at runtime. This external dependency is not a verified or trusted source, creating a supply chain vulnerability. - [COMMAND_EXECUTION]: The skill requires the execution of shell commands (
npx) to install its core functionality, granting the agent power to interact with the system environment. - [PROMPT_INJECTION]: A hidden Unicode character (U+2028) was detected in the frontmatter description field. Such characters are used in steganographic techniques to hide malicious instructions or bypass prompt filters.
Recommendations
- AI detected serious security threats
Audit Metadata