Skills
Navigate
skills/zazencodes/skills/init-agents-md/Gen Agent Trust Hub

init-agents-md

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files to generate instructional content for agents.
  • Ingestion points: The skill reads CLAUDE.md to use as 'seed material' and the README as an initial guide (SKILL.md, Workflow steps 1 & 2).
  • Boundary markers: Absent. There are no instructions provided to separate the ingested data from the agent's instructions or to ignore embedded prompts within those files.
  • Capability inventory: The skill has the ability to execute shell commands (ln, rg, ls) and write files to the repository (SKILL.md).
  • Sanitization: Absent. The content extracted from the existing files is used to draft the new AGENTS.md without validation or escaping.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for file system manipulation and repository exploration.
  • Evidence: The workflow explicitly calls for running ln -sf AGENTS.md CLAUDE.md to create symlinks and using rg or ls to inspect the project structure (SKILL.md, Workflow steps 2 & 4).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 11:21 PM