ktlo
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Linear issue descriptions and details) which could contain malicious instructions.
- Ingestion points: The instructions in SKILL.md direct the agent to fetch issue details using the Linear MCP server.
- Boundary markers: The prompt does not define specific delimiters or instructions to ignore embedded commands within the fetched issue data.
- Capability inventory: The skill implies the agent will be used to plan and potentially implement code based on the fetched content.
- Sanitization: There is no evidence of sanitization or validation of the fetched issue content before processing.
Audit Metadata