linear-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses project-local files as a source of truth for its routing and publishing logic, which creates a potential vector for instructions embedded in those files to influence agent behavior.
- Ingestion points: Reads from project files including
AGENTS.md,CLAUDE.md,docs/agents/issue-tracker.md, and.pi/settings.json(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings when processing the contents of these configuration files.
- Capability inventory: The skill utilizes capabilities to create and fetch issues via the Linear API (
linear_tracker_create_issue,linear_tracker_resolve, and Linear MCP tools). - Sanitization: There are no explicit instructions for sanitizing or validating the data retrieved from the local configuration files before it is used to drive tool execution.
- [NO_CODE]: The skill is entirely instructional and does not include any accompanying scripts, executables, or implementation code.
Audit Metadata