ticket
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from an external project management platform.
- Ingestion points: The skill retrieves issue descriptions and comments using
mcp__linear-server__get_issueandmcp__linear-server__list_comments(documented inSKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the retrieved content as data rather than instructions.
- Capability inventory: The agent has the capability to modify tickets (
save_issue), perform git operations (branch checkouts), and likely execute code as part of the 'Build' phase (referencingfull-stoporfull-sendskills). - Sanitization: No sanitization or validation of the content retrieved from Linear is mentioned, creating a surface where malicious instructions embedded in a ticket could influence the agent's actions.
Audit Metadata