flow-next-opencode-rp-explorer
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
rp-clicommand-line tool to perform codebase analysis tasks. Examples include executingrp-cli -e 'tree',rp-cli -e 'structure .', andrp-cli -e 'read <path>'. These commands run locally to facilitate the agent's exploration of the project. - [PROMPT_INJECTION]: The skill operates on content retrieved from the local codebase, which presents a surface for indirect prompt injection if the files being read contain malicious instructions targeted at the agent.
- Ingestion points: The agent ingests untrusted data from the filesystem using commands like
rp-cli -e 'read <file>'andrp-cli -e 'search <pattern>'(documented inSKILL.mdandcli-reference.md). - Boundary markers: The instructions do not define any delimiters or system-level instructions to ignore potential commands embedded within the code being analyzed.
- Capability inventory: The skill allows the agent to read any file in the workspace and write aggregated context to local markdown files (e.g.,
rp-cli -e 'context --all > codebase-map.md'), combining read and write capabilities. - Sanitization: There is no mention of sanitizing or validating the contents of the files before they are processed by the agent.
Audit Metadata