glossary-management
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local TypeScript scripts via the
bunruntime for synchronization and validation tasks. - Evidence: Commands such as
bun ~/.claude/tools/bin/glossary-sync.tsandbun ~/eon/cc-skills/plugins/itp-hooks/hooks/posttooluse-terminology-sync.tsinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple project-level markdown files, creating an attack surface where embedded instructions could influence agent behavior.
- Ingestion points: Reads from project
CLAUDE.mdfiles found in directories specified by theSCAN_PATHSconfiguration (e.g.,~/eon/*/CLAUDE.md). - Boundary markers: Relies on a specific 5-column markdown table schema for identifying and extracting terminology data.
- Capability inventory: The skill utilizes
Bash,Read,Edit, andGreptools, which allow it to modify local files and execute maintenance scripts. - Sanitization: No explicit logic or instructions are provided to sanitize, escape, or ignore natural language instructions that might be embedded within the ingested markdown files.
Audit Metadata