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/clipackage 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, andsearch-issuesinSKILL.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 themembrane requestcommand. - Sanitization: There is no mention of sanitization or filtering for the external content retrieved from GitHub.
Audit Metadata