linear-create
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository planning documents to generate Linear artifacts, creating a potential vector for instructions in those files to influence agent behavior.\n
- Ingestion points: Document discovery phase in SKILL.md reads PRODUCT.md, ARCHITECTURE.md, and IMPLEMENTATION.md from the repository root or docs/ directory.\n
- Boundary markers: The instructions do not specify the use of delimiters or warnings to separate untrusted document content from the agent's instructions.\n
- Capability inventory: The skill is capable of creating and modifying issues, projects, initiatives, and documents in Linear, and can perform binary file uploads to Linear's infrastructure.\n
- Sanitization: Extracted content is drafted into Linear descriptions without explicit sanitization or escaping of potential prompt injection sequences.
Audit Metadata