skills/marcioaltoe/skills/find-rules/Gen Agent Trust Hub

find-rules

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to search and analyze local project files (e.g., .cursor/rules, CLAUDE.md, ARCHITECTURE.md) to provide the user with relevant development constraints and patterns.
  • [COMMAND_EXECUTION]: The skill utilizes 'Glob' and 'Grep' tools to perform structured file discovery and content searching within the project directory. These operations are restricted to the local file system and are used for their intended purpose of navigating project documentation.
  • [PROMPT_INJECTION]: Analysis of the instructions revealed no attempts to override agent safety protocols, extract system prompts, or bypass constraints. The use of 'CRITICAL' and 'MANDATORY' within the text refers to the enforcement levels of the project rules being discovered, not to the agent's internal behavior instructions.
  • [DATA_EXFILTRATION]: There are no network-capable tools (like curl or wget) requested or used in the skill, and no instructions suggest sending local file content to external endpoints.
  • [EXTERNAL_DOWNLOADS]: The skill does not download external scripts, packages, or configurations. It relies entirely on the existing files within the user's project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 02:07 AM
Security Audit — agent-trust-hub — find-rules