tally-rewind

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate performance-benchmarking workflow, but measure.sh disables Composer's security blocking and audit for every dependency install at old commits, a protection weakening beyond what the task needs, though it is disclosed in a comment and confined to throwaway worktrees.

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow reads GitHub merged pull requests and their descriptions via gh (SKILL.md line 46), which are outsider-authored free text from external contributors, and this is a GitHub PR reading path, so it is medium.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 02:15 PM
Issues
2