scrape

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 is a read-only scraper, but its claim that "nothing is written anywhere but stdout" is contradicted by undisclosed writes: it edits the repo's .git/info/exclude, creates .gstack/tmp files, and logs telemetry and learnings, so it hides some of its own activity from the user.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow drives Aside to open a user-specified arbitrary web page and reads its text, snapshot, and console output, so outsider-authored content is ingested only after the agent actively fetches a chosen URL, which is the low-risk "selected URL" case.

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, 08:17 PM
Issues
2