Skills
skills/adonis0123/adonis-skills/agent-symlink-init/Gen Agent Trust Hub

agent-symlink-init

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including mkdir -p and ln -sfn to initialize standardized directory structures and establish symbolic links within the repository.
  • [COMMAND_EXECUTION]: The skill performs targeted deletion of legacy directories and scripts, such as .ruler and sync-llm-skills.ts, to remove deprecated migration automation.
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository files to perform automated edits, creating an indirect injection surface. Ingestion points: package.json and .gitignore in the repository root. Boundary markers: Absent. Capability inventory: mkdir, ln, rm, and file-write operations across ALL scripts. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:54 AM