daily-meeting-update

Fail

Audited by Snyk on Feb 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 0.90). The prompt explicitly instructs "Silent Detection" to probe local files and tooling presence "silently (suppress errors, don't show to user)," which is a hidden/deceptive instruction that contradicts the skill's stated consent-before-access principle and falls outside the advertised interactive standup purpose.

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly pulls and displays user-generated third-party content from GitHub/Git (via gh/git) and Jira (via jira CLI) — e.g., commits, PRs, reviews, and ticket descriptions in "Phase 1: Pull GitHub/Jira Data" and then "show pulled data as context" during the Phase 2 interview — which exposes the agent to untrusted external content that could contain indirect prompt injections.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 10:18 PM