pr-naming-convention

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script scripts/check_pr.py using Python. This script is part of the skill package and uses standard libraries to perform regex validation without any risky operations like network access or file system modifications.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user input by passing it as command-line arguments to a script.
  • Ingestion points: Untrusted user input enters the agent context when a user asks to validate a title or branch name, which is then passed to the validation script.
  • Boundary markers: Absent; the instructions do not specify using delimiters for user-provided strings.
  • Capability inventory: The agent uses shell command execution to run the validator script.
  • Sanitization: Absent; the skill does not include logic to sanitize or escape user input for the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:05 AM
Security Audit — agent-trust-hub — pr-naming-convention