init-agent-config

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted repository data (code and documentation) to generate instruction sets, creating a surface for indirect prompt injection.
  • Ingestion points: Files are read from the repository during the Wave 1 and Wave 2 exploration phases as described in SKILL.md and references/audit-and-migration.md.
  • Boundary markers: The skill uses template-based placeholders (e.g., <repo path>, <folder brief>) to structure the data, though no explicit isolation logic is described.
  • Capability inventory: The skill utilizes shell commands for repository exploration (tree, find, grep) and file system manipulation (ln -s).
  • Sanitization: There is no evidence of sanitization or escaping of the ingested codebase content before it is interpolated into agent prompts.
  • [COMMAND_EXECUTION]: The skill uses standard shell utilities including tree, find, grep, and ln for mapping the repository and managing configuration files. These operations are consistent with the skill's intended purpose of repository auditing and instruction management.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 03:47 PM