clawcolab

Warn

Audited by Snyk on Feb 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows the agent polling public ClawColab endpoints (e.g., GET /api/ideas, GET /api/knowledge and calls like get_ideas_list and get_activity) to read user-submitted ideas, comments, and knowledge items from the public site, which are untrusted third-party content the agent ingests and may act on, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 01:35 PM