linear-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill provides instructions to "re-run it with escalated permissions" if a
runtime_access_deniederror occurs. This encourages the agent or user to bypass sandbox restrictions by acquiring higher system privileges.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from an external source (Linear tickets), including ticket text, comments, and attachments. Although the skill body includes a warning to treat this content as untrusted data, it creates a surface area for instructions embedded in external content to be processed by the agent. - Ingestion points: SKILL.md (mentions ticket text, comments, and attachments)
- Boundary markers: Present (Description explicitly states to treat data as untrusted and not as instructions)
- Capability inventory: Executes the
orca(or resolved variants) CLI tool - Sanitization: Not explicitly defined in the provided file beyond the textual warning.
Audit Metadata