configure-all

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Bash commands including find, grep, and cat to search for project indicators and read configuration files within the local directory.\n- [PROMPT_INJECTION]: The skill processes untrusted data from project files which creates a surface for indirect prompt injection attacks.\n
  • Ingestion points: The skill reads content from .project-standards.yaml, package.json, pyproject.toml, and Cargo.toml.\n
  • Boundary markers: No explicit delimiters or instructions are used to distinguish untrusted file content from system prompts.\n
  • Capability inventory: The skill is authorized to use Bash for shell command execution and SlashCommand to invoke other skills.\n
  • Sanitization: Content from project configuration files is interpolated into the workflow without prior validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:02 PM