aris-monitor-experiment
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's workflow (SKILL.md) instructs the agent to pull and parse external, user-generated experiment data—notably "Step 3.5: Pull W&B Metrics" (Weights & Biases runs via the wandb API) and to query Vast.ai/Modal instance status and logs—which the agent reads and interprets to drive monitoring decisions, exposing it to untrusted third-party content that could carry injected instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata