ci-tests
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute stack-specific test commands such asuv run pytest,pnpm vitest, andcargo test. These commands are constructed dynamically based on file system detection. - [PROMPT_INJECTION]: The skill interpolates the
$ARGUMENTSvariable directly into shell command strings. Since this input is not sanitized or escaped, it presents a potential command injection vector where shell metacharacters (e.g.,;,&&,|,`) could be used to execute unauthorized commands. - [PROMPT_INJECTION]:
- Ingestion points: User-supplied strings via the
$ARGUMENTSparameter inSKILL.mdare processed at runtime. - Boundary markers: No delimiters or boundary markers are used to isolate the user input from the shell command template.
- Capability inventory: The skill is granted access to the
Bashtool, allowing it to execute arbitrary shell commands on the host environment. - Sanitization: There is no evidence of input validation, escaping, or sanitization before the input is passed to the shell.
Audit Metadata