pytest-coder
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (HIGH): Indirect Prompt Injection vulnerability surface.
- Ingestion points: The skill is designed to analyze project code using
Read,Grep, andGlobtools to generate relevant tests. - Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to distinguish between project data and instructions.
- Capability inventory: The skill frontmatter explicitly permits the use of
Bash(command execution),Write(file creation), andEdit(file modification). - Sanitization: Absent. There are no instructions for the agent to sanitize, escape, or validate the content of the files it reads before using that content to formulate commands or write new files.
- [COMMAND_EXECUTION] (MEDIUM): The skill frontmatter allows the
Bashtool, which permits arbitrary command execution on the host. While its intended use is runningpytest, the lack of constraints on this tool makes it a significant risk factor if the agent's reasoning is compromised.
Recommendations
- AI detected serious security threats
Audit Metadata