Command Development

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill teaches the use of bash execution syntax (!\command`) to gather dynamic context such as repository status or environment variables. It explicitly guides developers to use the allowed-toolsfrontmatter field to restrict bash execution to specific command patterns (e.g.,Bash(git:*)), significantly reducing the attack surface.\n- **[DATA_EXFILTRATION]:** The documentation describes the @syntax for including file contents in prompts. To prevent unauthorized file access, it provides 'Validation Patterns' that demonstrate how to verify file existence and validate user-supplied paths before they are processed by the agent.\n- **[PROMPT_INJECTION]:** The skill provides instructions on ingesting user-supplied data via positional arguments ($1, $2) and the$ARGUMENTS` variable.\n
  • Ingestion points: Untrusted data enters the agent context through CLI arguments defined in SKILL.md and frontmatter-reference.md.\n
  • Boundary markers: The skill suggests using clear instructional headers and framing to separate data from instructions.\n
  • Capability inventory: Examples demonstrate potential subprocess execution (git, npm, gh), file-reading, and file-writing tools across the examples/ and references/ directories.\n
  • Sanitization: The skill contains a dedicated 'Validation Patterns' section in SKILL.md and plugin-features-reference.md that teaches developers how to perform input validation and existence checks to ensure that untrusted data does not lead to unintended command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 03:11 AM
Security Audit — agent-trust-hub — Command Development