compare
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute specific internal scripts (audit.mjs,compare.mjs,snapshot.mjs) located within the${CLAUDE_PLUGIN_ROOT}directory. This is used to perform audits and generate comparisons. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from external websites and search results, which constitutes a potential attack surface for indirect prompt injection.
- Ingestion points: Content is ingested from external URLs via the snapshot and audit functions, as well as from the output of the
WebSearchtool. - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard potential instructions embedded within the retrieved external data.
- Capability inventory: The skill can execute shell commands via
Bash(restricted to plugin scripts), perform web searches, and read/glob files within the plugin's data and root directories. - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is presented to or processed by the AI agent.
Audit Metadata