codometer-configure

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to analyze a repository's structure and contents to generate or modify configuration files (e.g., codometer.config.ts) and update documentation such as README.md. This ingestion of untrusted data from the repository creates a potential surface for indirect prompt injection. \n- Ingestion points: The agent reads file paths, naming conventions, and codebase metrics from the local repository (SKILL.md).\n- Boundary markers: The instructions do not specify the use of delimiters or clear instructions to disregard embedded commands within the ingested repository data.\n- Capability inventory: The agent possesses the capability to write and overwrite configuration files and project documentation based on its analysis.\n- Sanitization: No explicit sanitization, validation, or escaping of repository-sourced data is mentioned before that data is used to populate configuration fields or documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 10:51 PM