ljg-xray-skill
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the shell command
dateto generate timestamps for Denote-style file naming and internal document metadata. - [COMMAND_EXECUTION]: Executes
grepto extract headers from the local file~/Documents/know/issues.orgto identify active discussion points for its cognitive baseline. - [EXTERNAL_DOWNLOADS]: Utilizes a
WebFetchmechanism to retrieve content from external URLs provided by the user for dissection. - [PROMPT_INJECTION]: Subject to Indirect Prompt Injection (Category 8). Ingestion points: Reads external skill definitions from
~/.claude/skills/and arbitrary web content viaWebFetch. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing external content. Capability inventory: Executes shell commands (date,grep), reads personal knowledge files, and writes reports to the local filesystem. Sanitization: No validation or filtering of the fetched external content is performed before analysis.
Audit Metadata