github

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is a vendor-provided tool necessary for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by ingesting and processing untrusted data from GitHub.
  • Ingestion points: The skill retrieves external data using actions such as list-issues, get-issue, list-pull-requests, and search-issues in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or warnings to prevent the agent from following instructions embedded within GitHub issues or pull requests.
  • Capability inventory: The skill possesses write capabilities including create-issue, update-issue, merge-pull-request, and arbitrary API access via the membrane request command.
  • Sanitization: There is no mention of sanitization or filtering for the external content retrieved from GitHub.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 04:55 PM