diffity-resolve-tree
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
diffityCLI tool globally usingnpm install -g diffityif the executable is not found on the system. - [COMMAND_EXECUTION]: The skill invokes several
diffityCLI commands (list, reply, resolve, dismiss) to manage repository comments and review sessions. - [INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted data from external comment threads, which can be manipulated to influence agent behavior.
- Ingestion points: Untrusted comment bodies are ingested via the
diffity agent list --jsoncommand output (referenced in SKILL.md). - Boundary markers: The instructions lack boundary markers or specific warnings to ignore instructions embedded within the fetched comments.
- Capability inventory: The agent has the capability to write to the file system (making code fixes and refactors) and execute network-connected CLI tools.
- Sanitization: There is no explicit sanitization or validation of the comment content before it is used to determine code changes.
Audit Metadata