bash-style-guide

Warn

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in 'SKILL.md' direct the agent to execute local Python scripts, specifically 'scripts/resolve_style_guides.py' and 'scripts/validate_trigger_matrix_sync.py'. These scripts are external to the skill package, creating a dependency on the local environment and the potential for executing malicious code if an attacker can control those file paths.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core function of processing untrusted user-provided Bash scripts and CI configuration files.
  • Ingestion points: The skill triggers on and reads content from '.sh' files, files with Bash shebangs, and YAML workflow files (SKILL.md).
  • Boundary markers: There are no boundary markers or explicit instructions to the agent to disregard natural language instructions embedded within the analyzed code files.
  • Capability inventory: The agent is granted the capability to execute shell commands, run Python scripts, and invoke multiple linting and testing tools (SKILL.md, references/quality-gate-command-matrix.md).
  • Sanitization: The skill lacks requirements for sanitizing or validating the contents of the analyzed files before they are processed by the agent or passed to external tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 08:38 PM