diffity-resolve-tree
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to install the
diffityCLI tool globally usingnpm install -g diffityif it is not found on the system. - [COMMAND_EXECUTION]: The skill relies on executing various shell commands through the
diffityCLI tool, such asdiffity agent list,diffity agent reply, anddiffity agent resolve, to interact with the repository review session. - [PROMPT_INJECTION]: The skill is designed to read and act upon comment threads from an external 'tree browser' which provides untrusted data that could influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent context through the JSON output of
diffity agent list --status open --json, specifically thebodyfield of the comments. - Boundary markers: The instructions lack delimiters or specific warnings to the agent to treat the comment text as data rather than instructions.
- Capability inventory: The agent is authorized to perform file system modifications (code fixes, refactors, documentation updates) and execute CLI replies based on the content of these comments.
- Sanitization: There is no logic provided to sanitize or validate the content of the comments before the agent interprets them as actionable requests.
Audit Metadata