erk-diff-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security risks detected. The skill is limited to providing a structured prompt for generating commit messages.
- [NO_CODE]: The skill consists entirely of Markdown text and contains no executable code, shell scripts, or external dependencies.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted git diff data, though the risk is minimal due to lack of capabilities. * Ingestion points: Git diff content processed by references/commit-message-prompt.md. * Boundary markers: Absent; no delimiters isolate the diff content from the instructions. * Capability inventory: None; the skill does not possess scripts, network access, or command execution. * Sanitization: None; the skill relies on the model's safety filters.
Audit Metadata