continuous-learning-v3
Fail
Audited by Snyk on Mar 14, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). The URLs point to a GitHub repo from an individual account that instructs you to install and run a plugin (JavaScript) which will execute in your environment and observe sessions — not an obvious binary download but potentially risky because it runs arbitrary code and may access sensitive data without strong provenance or many community signals.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's CLI explicitly fetches and ingests arbitrary HTTP(S) URLs in scripts/instinct-cli.py (cmd_import), importing remote, user-provided "instinct" files which are then added to the agent's instincts and can change behavior, so untrusted third-party web content can influence tool decisions.
Issues (2)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata