meaningful-linear-issues

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data from the Linear platform and possesses capabilities to modify state on that platform. \n
  • Ingestion points: The skill retrieves data from the Linear API using tools such as get_issue, list_issues, list_projects, list_users, and list_milestones as described in SKILL.md. \n
  • Boundary markers: The instructions do not define specific delimiters or safety instructions for the agent to use when interpreting content retrieved from the external Linear source. \n
  • Capability inventory: The skill possesses write and modification capabilities through tools like save_issue, removeBlocks, removeBlockedBy, and removeRelatedTo as specified in SKILL.md. \n
  • Sanitization: The skill's instructions do not include logic for sanitizing or validating external data before the agent uses it to perform further actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:14 PM
Security Audit — agent-trust-hub — meaningful-linear-issues