setup-engineering-workflows
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection due to its behavior of reading untrusted external data and possessing significant write capabilities within the repository.
- Ingestion points: The skill explores repository files, including
AGENTS.md,CLAUDE.md, anddocs/adr/, and retrieves content from issue trackers (titles, descriptions, and comments) using GitHub and GitLab CLI tools. - Boundary markers: The instructions do not define clear boundaries or markers to separate untrusted repository content from the agent's instructions, nor do they instruct the agent to ignore potentially malicious embedded commands within that content.
- Capability inventory: The skill has the capability to write directly to instruction files (
AGENTS.md/CLAUDE.md) and create project documentation indocs/agents/. It also performs automated write operations on remote issue trackers through CLI commands. - Sanitization: There is no evidence of sanitization or validation of the ingested data before it is processed or written to persistent repository files.
Audit Metadata