session-inspector

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and combines GitHub issue comments via the "extract-session-from-issue" workflow (see SKILL.md / references/tools.md: "Extracts and combines chunked session content from GitHub issue comments"), which are public user-generated inputs that the agent parses and uses to reconstruct sessions and drive follow-up actions like creating PRs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). This skill's "extract-session-from-issue" feature fetches GitHub issue comments at runtime (e.g. https://github.com/owner/repo/issues/123) and combines chunked session content into session XML that can be injected into the agent's context, so remote issue content can directly control prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 03:25 PM