linear
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves reading and analyzing 'thoughts' documents from the local filesystem to generate Linear tickets. Since these documents may contain untrusted content, they present a surface for indirect prompt injection where hidden instructions could influence ticket content or metadata.\n
- Ingestion points: The process begins by reading external files as described in
references/creating-tickets.md(Step 1).\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the ingested documents.\n
- Capability inventory: The skill possesses the ability to write tickets via the
linearisCLI and has file system access through theRead,Write, andGreptools.\n - Sanitization: No specific sanitization or structural validation is implemented for the content extracted from 'thoughts' documents prior to ticket drafting, relying solely on model reasoning.
Audit Metadata