changelog-generator
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git logto retrieve the commit history required to generate the changelog. This is a legitimate use of command execution for the skill's purpose. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes git commit messages which are external, potentially untrusted data. If a commit message contains malicious instructions, it could influence the agent's behavior during the summary generation process.
- Ingestion points: Commit messages retrieved via the
git logcommand. - Boundary markers: No specific delimiters or warnings are used in the instructions to isolate the commit content from the agent's core instructions.
- Capability inventory: The skill is capable of executing shell commands (
git log) and generating file content (outputting aCHANGELOG.md). - Sanitization: No explicit sanitization or filtering of the commit message content for prompt injection patterns is described.
Audit Metadata