update-issue-requirements
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Linear issues (descriptions and comments), which introduces a surface for indirect prompt injection attacks where instructions embedded in the issue could influence agent behavior.
- Ingestion points: Step 2 requires the agent to read the current description and all comments from a Linear issue.
- Boundary markers: The workflow lacks explicit boundary markers or instructions to treat issue content as data rather than instructions.
- Capability inventory: The skill uses Linear MCP tools to modify descriptions and add comments. It does not have access to shell execution, arbitrary file system writes, or network operations outside of the Linear platform integration.
- Sanitization: There are no instructions to sanitize or validate the external text retrieved from the Linear issue before it is interpolated into the agent's context.
Audit Metadata