Skills
skills/yistc/skills/yistc-linear-research/Gen Agent Trust Hub

yistc-linear-research

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from an external platform (Linear).
  • Ingestion points: get_issue and list_comments tools are used to retrieve potentially attacker-controlled text as described in SKILL.md.
  • Boundary markers: The skill does not define clear delimiters or instruct the agent to ignore instructions embedded within the retrieved issue data.
  • Capability inventory: The skill utilizes save_comment and delete_comment tools, providing a write-back path to the external platform.
  • Sanitization: There is no evidence of input validation or sanitization for the data retrieved from Linear before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 12:58 PM
Security Audit — agent-trust-hub — yistc-linear-research