run-experiment
Warn
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill encourages storing sensitive information such as the
WANDB_API_KEYin theCLAUDE.mdfile. It then reads this secret and executes it as a plain-text argument in a shell command over SSH (wandb login <WANDB_API_KEY>), which exposes the credential in process listings and shell history on the target server. Additionally, the skill accesses the sensitive configuration file~/.claude/feishu.jsonto send notifications. - [INDIRECT_PROMPT_INJECTION]: The skill reads instructions and parameters from a project's
CLAUDE.mdand uses them to construct bash and SSH commands. A malicious project could contain injected shell commands within fields likeSSH:,Conda:, orCode dir:, leading to unauthorized code execution when the agent attempts to deploy an experiment. - Ingestion points: Read of
CLAUDE.md,vast-instances.json, and~/.claude/feishu.json. - Boundary markers: None present; the agent processes and interpolates file content directly into command strings.
- Capability inventory:
Bash(*),Write,Edit, and SSH-based remote command execution. - Sanitization: No evidence of input validation or escaping for configuration values retrieved from the file system.
- [DYNAMIC_EXECUTION]: The deployment workflow for Modal serverless GPU involves the automated generation of a
modal_launcher.pyscript which is then executed at runtime. Furthermore, the skill uses theEdittool to programmatically inject code (W&B initialization and logging) into user-provided training scripts, creating a risk of unintended code execution if the injection points are manipulated. - [COMMAND_EXECUTION]: The skill relies extensively on executing arbitrary bash commands locally and via SSH to manage environments and training jobs. The use of shell wrappers with interpolated variables (
<conda_path>,<env>,<script>,<args>) provides a significant attack surface for command injection if the environment configuration is untrusted.
Audit Metadata