linear
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto execute GraphQL queries and mutations against the Linear API as described in SKILL.md. - [EXTERNAL_DOWNLOADS]: Fetches data and sends updates to
api.linear.app. This is the official endpoint for Linear, a well-known project management service. - [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it retrieves and processes untrusted data from an external source.
- Ingestion points: Content enters the agent context via issue titles, descriptions, and comment bodies fetched in the
issueSearchandissuequeries in SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore instructions that might be embedded in the retrieved issue data.
- Capability inventory: The agent can use
curlto perform network operations, including mutations that modify states or create comments on the Linear platform as shown in SKILL.md. - Sanitization: Absent. There is no evidence of filtering or sanitizing the content retrieved from the API before it is presented to the model.
Audit Metadata