linear
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Linear GraphQL API. All command patterns are static and target the official Linear API endpoint (https://api.linear.app/graphql). User inputs (e.g., issue titles, descriptions) are passed as data payloads in JSON format rather than shell arguments, which is a safe practice. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Linear API, including issue titles, descriptions, comments, and documents. An attacker with access to the Linear workspace could embed malicious instructions in these fields to influence the agent's behavior.
- Ingestion points: Linear API responses (issues, projects, documents, comments) fetched in
SKILL.mdandscripts/linear_api.py. - Boundary markers: None identified in the provided instructions; the agent processes the raw output of curl/Python script.
- Capability inventory: The agent has capabilities to execute shell commands (
curl), file writes (via standard platform tools), and further API interactions. - Sanitization: None. The Python script and curl commands emit raw JSON data directly into the agent's context.
Audit Metadata