sharpen

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill tells the agent to sharpen the task's approach and keep an outside correctness check, but it also says to do so "without narrating the framing," which asks the agent to hide the skill's own activity from the user, a mild concealment that fits the medium category.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow asks the agent to research "how a top expert would approach this task" and their "raw sources," which implies active web searching or fetching of arbitrary outsider-authored content, but it names no specific service or monitored feed.

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 16, 2026, 07:57 AM
Issues
2