forge-idiomatic-engineer

Pass

Audited by Gen Agent Trust Hub on May 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates project management through the execution of a local shell script (scripts/orient.sh) and various CLI commands (forge, cargo, sqlx-cli). These tools are used to inspect the environment, validate configuration, and discover project handlers. Each command is intended for local environment discovery and project maintenance.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from the local repository to perform its functions, representing an indirect prompt injection surface.\n
  • Ingestion points: Files including forge.toml, src/main.rs, and migration SQL files are read by the orient.sh script and the agent to orient itself within the codebase.\n
  • Boundary markers: The skill does not explicitly define markers or system instructions to ignore embedded instructions in the ingested code or configuration files.\n
  • Capability inventory: The skill instructions and associated scripts grant the agent the capability to execute shell commands, read and write local files, and interact with development services like Docker and PostgreSQL.\n
  • Sanitization: There is no evidence of sanitization or filtering of the content read from the repository files before it is processed or added to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 22, 2026, 06:46 AM