AGENT LAB: SKILLS

fal-platform

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt instructs embedding the API key directly into CLI commands (e.g., --add-fal-key "your_key_here") which requires the agent or user to place secret values verbatim in generated commands/output, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's scripts call external fal.ai APIs (e.g., scripts/requests.sh GET /models/requests/by-endpoint and then echo/parse the raw $RESPONSE, and scripts/pricing.sh and usage.sh similarly output API responses), which can include user-generated request payloads or other untrusted data that the agent reads and displays, exposing it to indirect prompt injection.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:29 PM