bun-test
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executebun testcommands, which is its primary intended function as described inSKILL.md. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection or command injection due to the direct interpolation of user-supplied arguments into shell commands.
- Ingestion points: The
patternargument defined in the frontmatter ofSKILL.mdis used as a shell variable in the execution examples. - Boundary markers: There are no boundary markers or delimiters provided to signal that the pattern should be treated as untrusted data.
- Capability inventory: The skill utilizes the
Bashtool to run commands as documented inSKILL.md. - Sanitization: No input validation, escaping, or sanitization logic is present for the
$PATTERNvariable before it is passed to the shell.
Audit Metadata