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_ROOT environment 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 list command.
  • 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
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:10 AM
Security Audit — agent-trust-hub — reviewr-comments