ln-500-story-quality-gate

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs standard git operations including commit, push, and worktree management. These commands utilize variables such as story IDs and titles derived from the project environment.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes data from external task management sources and git branch names.\n
  • Ingestion points: The skill reads story metadata from Linear and local markdown files, and extracts identifiers from git branch names.\n
  • Boundary markers: While it references external guides for input resolution, it does not explicitly define delimiters or boundary markers for untrusted data in the main skill logic.\n
  • Capability inventory: The skill possesses the ability to read and write files, execute git commands, and invoke other sub-skills (ln-510, ln-520).\n
  • Sanitization: No explicit sanitization or validation of externally provided strings (such as story titles or branch names) before their use in command templates or prompt context is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 05:26 PM