linear-impl-logger

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided summaries and artifact metadata, which represents a surface for indirect prompt injection if malicious instructions are present in the ingested data.
  • Ingestion points: Inputs like Summary, Artifacts, and commit messages obtained via git history in SKILL.md.
  • Boundary markers: None specified; the skill renders markdown directly from inputs.
  • Capability inventory: Interacts with Linear and Notion APIs to save comments and pages.
  • Sanitization: No mention of sanitizing input before inclusion in the final log.
  • [COMMAND_EXECUTION]: The skill uses local git and grep commands to extract implementation details from the repository history.
  • Evidence: The backfilling logic explicitly calls for git log, git show, and grep to identify files and code patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 07:40 AM
Security Audit — agent-trust-hub — linear-impl-logger