github-sync
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from local markdown files to generate GitHub issues and project metadata, creating a surface for indirect prompt injection.\n
- Ingestion points: Workflow steps in
SKILL.mdread file content from.artifacts/implementation-artifacts/and.artifacts/planning-artifacts/.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested text, although a mandatory human review of a "Sync Report" is required before any actions are taken.\n
- Capability inventory: The skill utilizes the
ghCLI for network operations and project management, and executes a local Python script (scripts/parse-artifacts.py) for data parsing.\n - Sanitization: The skill does not perform explicit sanitization or escaping of the ingested markdown content before pushing it to GitHub issues.
Audit Metadata