plugin-fleet-sweep
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands and scripts as part of the plugin lifecycle. This includes running
typecheck,tests,build, andgitoperations (commit, tag, push). It also mentions executing a repository-specific script,sync-mirrors.mjs, which is described as a vendor-specific tool for the author's repositories. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads 'corridor cards' from
plugin-upgrade/references/, scans plugin source code (src/), and captures browser console/DOM output during live sweeps. - Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are present.
- Capability inventory: The agent uses
grep, headless browser instrumentation (CDP), build/test tools, and git synchronization scripts. - Sanitization: No sanitization or validation of the ingested external content is specified before it is used to drive the sweep workflow.
Audit Metadata