invoking-github

Warn

Audited by Snyk on May 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's github_client (scripts/github_client.py) and SKILL.md / references/iterating-integration.md explicitly read arbitrary files from GitHub repos (e.g., read_file and resume_session_from_github that fetch DEVLOG.md), meaning untrusted, user-generated repository content from the public web is ingested and can directly influence commits, PR creation, and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 7, 2026, 04:35 AM
Issues
1