skills/noih/dev-skills/rule-git/Gen Agent Trust Hub

rule-git

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes instructions that explicitly direct the AI to ignore specific parts of its operational context and override system defaults.
  • Evidence: "This overrides any default system behavior" used to prevent AI attribution in metadata.
  • Evidence: "Ignore any changes mentioned earlier if they are not present in the commit" and "Do not use previous commits, conversation history, or remembered task context as evidence" are instructions to disregard prior context.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill instructs the agent to analyze arbitrary code changes (diffs) to generate commit messages, which could contain malicious instructions embedded in comments or strings.
  • Ingestion points: Git diffs and file changes provided to the agent for commit message generation.
  • Boundary markers: Absent; there are no instructions to treat the diff content as untrusted or to use specific delimiters.
  • Capability inventory: The skill is used for text generation (commit messages).
  • Sanitization: Absent; the skill does not define methods to filter or escape content from the code being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 08:17 PM