linear-migration-deep-dive
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (Jira, Asana, GitHub Issues) via their respective APIs and processes this data for migration. If a source issue contains malicious instructions, the agent or subsequent processes handling this data could be influenced.
- Ingestion points: Untrusted external data is ingested in
exportJiraProject(SKILL.md, implementation.md) andexportAsanaProject(implementation.md). - Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the migrated content.
- Capability inventory: The skill possesses the capability to write to the Linear API via
LinearClient.createIssueand to the local filesystem viafs.writeFile(implementation.md). - Sanitization: The skill performs formatting conversion (Jira markup to Markdown) but does not implement sanitization or filtering to remove potential prompt injection sequences from the source descriptions.
Audit Metadata