linear
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves untrusted data from the external Linear platform, such as issue titles and descriptions. This creates a surface for indirect prompt injection if the agent reads an issue containing malicious instructions designed to subvert its behavior.\n
- Ingestion points: Issue data is ingested in
scripts/linearvia theshowandlistcommands.\n - Boundary markers: Absent. The skill does not currently use specific delimiters to isolate external content from the system prompt.\n
- Capability inventory: The agent can create and update issues or comments via the
save_issueandsave_commenttools.\n - Sanitization: Absent. Content from the Linear platform is provided to the agent without modification or validation.
Audit Metadata