skills/knoopx/pi/conventional-commits/Gen Agent Trust Hub

conventional-commits

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions were found that attempt to override agent behavior, bypass safety filters, or extract system prompts. The content is strictly limited to commit message formatting rules.
  • [Data Exposure & Exfiltration] (SAFE): There are no commands that access sensitive files, environment variables, or hardcoded credentials. No network operations (e.g., curl, fetch) are present.
  • [Remote Code Execution] (SAFE): The skill does not download or execute any remote scripts. It does not contain any logic for dynamic code generation or execution.
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted data (user descriptions of code changes) to generate formatted output.
  • Ingestion points: User input provided when asked to "write a commit message".
  • Boundary markers: Absent; the skill relies on the agent's natural processing of inputs.
  • Capability inventory: No capabilities for subprocess calls, file writing, or network operations are defined in this skill.
  • Sanitization: Absent. However, given the lack of executable capabilities, the risk is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 05:59 AM