estimate
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Linear tickets which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Ticket titles, descriptions, and comments fetched via the
lcCLI tool in Step 2. - Boundary markers: The instructions do not define any delimiters (like xml tags or triple quotes) to isolate the untrusted ticket data, nor do they instruct the agent to ignore instructions embedded within the ticket content.
- Capability inventory: The skill uses
git branchand thelcLinear CLI. While these tools have limited scope, the injected content could still manipulate the agent's output or affect other active skills in the session. - Sanitization: The skill lacks any steps to validate, filter, or sanitize the content retrieved from Linear before it is interpolated into the assessment context.
Audit Metadata