local-issue

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local system commands including Git operations (git add, git commit) and file system moves (mv) to manage issue lifecycles. It also executes a bundled Python script next-issue-id.py to calculate issue sequences.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to prioritize and adopt templates found within the target project's .issues/templates/ directory.
  • Ingestion points: Files located at .issues/templates/*.md within the active project directory.
  • Boundary markers: None. The skill does not include instructions to ignore or sanitize embedded instructions within external templates.
  • Capability inventory: The agent can perform file writes, directory listing, file movement (mv), and version control commits (git commit).
  • Sanitization: None. Content from project-specific templates is used directly to structure the agent's next actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:03 PM