reviewr-comments
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a CLI tool named
herdr-reviewr(or via the$HERDR_PLUGIN_ROOTenvironment variable). This is the primary mechanism for interacting with the comment store. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved via the
herdr-reviewr comment listcommand. - Ingestion points: Comments are read from an external store into the agent's context.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between valid data and potentially malicious instructions within the comments.
- Capability inventory: The agent can modify source code and interact with the comment lifecycle based on these inputs.
- Sanitization: No validation or sanitization is performed on the comment text before the agent acts upon it.
Audit Metadata