hunk-review
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content such as code diffs and hunk structures through the
hunk session reviewcommand. These data sources can be manipulated by external actors to include malicious instructions designed to hijack the agent's logic during a review session. - Ingestion points: Output from
hunk session review --jsonandhunk session review --include-patch(SKILL.md). - Boundary markers: The skill does not define specific delimiters or warnings to prevent the agent from following instructions embedded within the diff content.
- Capability inventory: The agent has the ability to execute shell commands via the
hunk session reloadfunctionality and can modify session comments and navigation. - Sanitization: No sanitization or verification mechanisms for the ingested diff data are specified.
- [COMMAND_EXECUTION]: The skill documentation describes the use of
hunk session reload -- <command>, which executes the provided command string through the Hunk CLI tool. While the intended use is for version control commands, this architectural pattern allows for arbitrary command execution if the agent is directed to use malicious inputs in the command field.
Audit Metadata