changelog-writer
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a standard git command to retrieve the project's recent version history.
- Evidence:
Run git log --onelinein SKILL.md. - [PROMPT_INJECTION]: The skill ingests untrusted data from git commit logs, which creates a surface for indirect prompt injection if commit messages contain malicious instructions.
- Ingestion points: Reads output from
git log --onelinein SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat commit messages as data only.
- Capability inventory: The skill has permissions to execute shell commands (
git log) and write to the local file system (CHANGELOG.md). - Sanitization: No explicit validation or filtering of the commit messages is performed before they are processed by the agent.
Audit Metadata