skills/seabbs/skills/org-standards/Gen Agent Trust Hub

org-standards

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at ~/.claude/scripts/org-standards.sh to gather repository configurations. It also utilizes the GitHub CLI (gh) and Git worktree commands to manage branches and pull requests.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of processing untrusted data.
  • Ingestion points: The skill reads and compares files across multiple repositories (e.g., .lintr, CI workflows, README.md) and monitors GitHub PR reactions and comments for state transitions (Phase 6).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the scanned files are defined.
  • Capability inventory: The agent possesses significant capabilities, including the ability to modify local files via Git worktree, push code to remote repositories, and create/manage pull requests using the GitHub CLI.
  • Sanitization: There is no evidence of sanitization or validation of the content read from external repositories before it is used to influence the agent's logic for propagating fixes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 07:16 AM