code-explain
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the command
jj diff -sto retrieve information about code changes within the local repository. - [EXTERNAL_DOWNLOADS]: The skill utilizes
WebSearchandWebFetchcapabilities to retrieve documentation for libraries and frameworks from external web sources. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from local code files and diff outputs.
- Ingestion points: Local source code files, output from
jj diff -s, and content retrieved viaWebFetch(SKILL.md, SUBAGENT.md). - Boundary markers: None identified; there are no explicit instructions to the model to ignore instructions embedded within the files being analyzed.
- Capability inventory: The skill can read local files, execute shell commands (
jj), access the internet (WebSearch/WebFetch), and spawn subagents (SUBAGENT.md). - Sanitization: No evidence of sanitization or filtering of the ingested code content before processing.
Audit Metadata